Skip to content
-
  • https://www.facebook.com/
  • https://twitter.com/
  • https://t.me/
  • https://www.instagram.com/
  • https://youtube.com/
AI Feed AI Feed AI Feed

AI news, tools, comparisons and practical guides

Subscribe
AI Feed AI Feed AI Feed

AI news, tools, comparisons and practical guides

  • AI News
  • AI Tools Radar
  • AI Comparisons
  • About
  • AI API Prices

Sections

  • AI Comparisons
  • AI Features
  • AI Guides
  • AI News
  • Uncategorized

Latest stories

  • AWS Details How to Deploy Interactive MCP Apps on AgentCore
  • xAI Makes Grok 4.6 Available in GitHub Copilot
  • Hugging Face and AWS Link Strands Robots to Streaming LeRobot Training
  • Anthropic Reports Claude Results in Protein Design and Chemistry
  • xAI Opens Grok Build to Every Plan on Web and Mobile
  • AI News
  • AI Tools Radar
  • AI Comparisons
  • About
  • AI API Prices
Subscribe
Close

Search

Home/AI API Token Prices and Request Calculator

AI API Token Prices and Request Calculator

AI MODEL PRICE INDEX

AI API token prices
and request calculator

Compare input and output token prices, calculate a real workload and track provider changes.

LAST UPDATESep 13, 2026 12:50Automatic hourly check
FLAGSHIP INDEX$6.09average for 1M mixed tokens
MODELS TRACKED445hourly catalogue scan
AVERAGE INPUT$1.92per 1M tokens
AVERAGE OUTPUT$8.94per 1M tokens
90-DAY PRICE HISTORYFlagship model price index
History collection has started. New real data points will appear every hour.
DeepSeek: DeepSeek V4 Pro 0423$2.400.00%Google: Nano Banana Pro (Gemini 3 Pro Image)$7.000.00%OpenAI: GPT-6 Astra$30.000.00%Anthropic: Claude Fable 5.1$30.000.00%

Choose a typical workload or enter your own values. Prices in the table are recalculated instantly.

PERSONAL COMPARISONSelect up to 4 models in the table

Use the + buttons next to model names.

ModelInput / 1MOutput / 1MChangeYour request
OpenAI: o1-pro⌄OpenaiLegacyVery expensive$150$6000%—
MODEL PROFILE

OpenAI: o1-pro

API profile based on provider metadata: image input, file input, coding, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
6 supported
Model ID
openai/o1-pro
Published
Mar 20, 2025
Open model documentation ↗
OpenAI: GPT-5.5 Pro⌄OpenaiVery expensive$30$1800%—
MODEL PROFILE

OpenAI: GPT-5.5 Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.5-pro
Published
Apr 24, 2026
Open model documentation ↗
OpenAI: GPT-5.4 Pro⌄OpenaiVery expensive$30$1800%—
MODEL PROFILE

OpenAI: GPT-5.4 Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.4-pro
Published
Mar 5, 2026
Open model documentation ↗
OpenAI: GPT-5.2 Pro⌄OpenaiVery expensive$21$1680%—
MODEL PROFILE

OpenAI: GPT-5.2 Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.2-pro
Published
Dec 10, 2025
Open model documentation ↗
OpenAI: GPT-5 Pro⌄OpenaiVery expensive$15$1200%—
MODEL PROFILE

OpenAI: GPT-5 Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5-pro
Published
Oct 6, 2025
Open model documentation ↗
OpenAI: GPT-5.5 Pro (batch)⌄OpenaiBatchVery expensive$15$900%—
MODEL PROFILE

OpenAI: GPT-5.5 Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.5-pro:batch
Published
Apr 24, 2026
Open model documentation ↗
OpenAI: GPT-5.4 Pro (batch)⌄OpenaiBatchVery expensive$15$900%—
MODEL PROFILE

OpenAI: GPT-5.4 Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.4-pro:batch
Published
Mar 5, 2026
Open model documentation ↗
OpenAI: o3 Pro⌄OpenaiVery expensive$20$800%—
MODEL PROFILE

OpenAI: o3 Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Files, Images
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o3-pro
Published
Jun 11, 2025
Open model documentation ↗
OpenAI: GPT-5.2 Pro (batch)⌄OpenaiBatchVery expensive$10.5$840%—
MODEL PROFILE

OpenAI: GPT-5.2 Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.2-pro:batch
Published
Dec 10, 2025
Open model documentation ↗
Anthropic: Claude Opus 4.1⌄AnthropicVery expensive$15$750%—
MODEL PROFILE

Anthropic: Claude Opus 4.1

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisLong contextLong responses
Context window
200K tokens
Maximum output
32K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
anthropic/claude-opus-4.1
Published
Aug 5, 2025
Open model documentation ↗
Anthropic: Claude Opus 4⌄AnthropicVery expensive$15$750%—
MODEL PROFILE

Anthropic: Claude Opus 4

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisLong contextLong responses
Context window
200K tokens
Maximum output
32K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Not declared
API features
8 supported
Model ID
anthropic/claude-opus-4
Published
May 22, 2025
Open model documentation ↗
OpenAI: GPT-4⌄OpenaiVery expensive$30$600%—
MODEL PROFILE

OpenAI: GPT-4

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
8.2K tokens
Maximum output
4.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
15 supported
Model ID
openai/gpt-4
Published
May 28, 2023
Open model documentation ↗
OpenAI: o1⌄OpenaiVery expensive$15$600%—
MODEL PROFILE

OpenAI: o1

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o1
Published
Dec 17, 2024
Open model documentation ↗
OpenAI: GPT-5 Pro (batch)⌄OpenaiBatchVery expensive$7.5$600%—
MODEL PROFILE

OpenAI: GPT-5 Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5-pro:batch
Published
Oct 6, 2025
Open model documentation ↗
OpenAI: GPT-6 Astra⌄OpenaiFlagshipVery expensive$10$500%—
MODEL PROFILE

OpenAI: GPT-6 Astra

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-6-astra
Published
Sep 4, 2026
Open model documentation ↗
OpenAI: GPT-6 Astra Pro⌄OpenaiFlagshipVery expensive$10$500%—
MODEL PROFILE

OpenAI: GPT-6 Astra Pro

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
openai/gpt-6-astra-pro
Published
Sep 4, 2026
Open model documentation ↗
Anthropic: Claude Fable 5.1⌄AnthropicFlagshipVery expensive$10$500%—
MODEL PROFILE

Anthropic: Claude Fable 5.1

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-fable-5.1
Published
Sep 1, 2026
Open model documentation ↗
Anthropic: Claude Fable 5⌄AnthropicFlagshipVery expensive$10$500%—
MODEL PROFILE

Anthropic: Claude Fable 5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
11 supported
Model ID
anthropic/claude-fable-5
Published
Jun 9, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.1 (batch)⌄AnthropicBatch$7.5$37.50%—
MODEL PROFILE

Anthropic: Claude Opus 4.1 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
32K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
anthropic/claude-opus-4.1:batch
Published
Aug 5, 2025
Open model documentation ↗
OpenAI: GPT-4 Turbo⌄Openai$10$300%—
MODEL PROFILE

OpenAI: GPT-4 Turbo

API profile based on provider metadata: image input, ai agents & tools, structured output.

Image inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
4.1K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-4-turbo
Published
Apr 9, 2024
Open model documentation ↗
OpenAI: GPT-4 Turbo Preview⌄OpenaiLegacy$10$300%—
MODEL PROFILE

OpenAI: GPT-4 Turbo Preview

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
128K tokens
Maximum output
4.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-4-turbo-preview
Published
Jan 25, 2024
Open model documentation ↗
OpenAI: GPT Chat Latest⌄Openai$5$300%—
MODEL PROFILE

OpenAI: GPT Chat Latest

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
6 supported
Model ID
openai/gpt-chat-latest
Published
May 5, 2026
Open model documentation ↗
OpenAI: GPT-5.5⌄Openai$5$300%—
MODEL PROFILE

OpenAI: GPT-5.5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.5
Published
Apr 24, 2026
Open model documentation ↗
OpenAI: GPT-6 Astra (batch)⌄OpenaiBatch$5$250%—
MODEL PROFILE

OpenAI: GPT-6 Astra (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-6-astra:batch
Published
Sep 4, 2026
Open model documentation ↗
OpenAI: GPT-6 Astra Pro (batch)⌄OpenaiBatch$5$250%—
MODEL PROFILE

OpenAI: GPT-6 Astra Pro (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-6-astra-pro:batch
Published
Sep 4, 2026
Open model documentation ↗
Anthropic: Claude Fable 5.1 (batch)⌄AnthropicBatch$5$250%—
MODEL PROFILE

Anthropic: Claude Fable 5.1 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-fable-5.1:batch
Published
Sep 1, 2026
Open model documentation ↗
Claude Opus 5⌄AnthropicFlagship$5$250%—
MODEL PROFILE

Claude Opus 5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-opus-5
Published
Jul 24, 2026
Open model documentation ↗
Anthropic: Claude Fable 5 (batch)⌄AnthropicBatch$5$250%—
MODEL PROFILE

Anthropic: Claude Fable 5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-fable-5:batch
Published
Jun 9, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.8⌄Anthropic$5$250%—
MODEL PROFILE

Anthropic: Claude Opus 4.8

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-opus-4.8
Published
May 27, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.7⌄Anthropic$5$250%—
MODEL PROFILE

Anthropic: Claude Opus 4.7

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
anthropic/claude-opus-4.7
Published
Apr 16, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.6⌄Anthropic$5$250%—
MODEL PROFILE

Anthropic: Claude Opus 4.6

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
anthropic/claude-opus-4.6
Published
Feb 4, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.5⌄Anthropic$5$250%—
MODEL PROFILE

Anthropic: Claude Opus 4.5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
64K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-opus-4.5
Published
Nov 24, 2025
Open model documentation ↗
OpenAI: GPT-5.4 Image 2⌄Openai$8$150%—
MODEL PROFILE

OpenAI: GPT-5.4 Image 2

API profile based on provider metadata: image input, file input, image generation, coding, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputImage generationCodingComplex analysisStructured outputLong contextLong responses
Context window
272K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Images, Text
Safety moderation
Enabled
API features
13 supported
Model ID
openai/gpt-5.4-image-2
Published
Apr 21, 2026
Open model documentation ↗
OpenAI: GPT-5 Image⌄Openai$10$100%—
MODEL PROFILE

OpenAI: GPT-5 Image

API profile based on provider metadata: image input, file input, image generation, coding, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputImage generationCodingComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Images, Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-5-image
Published
Oct 14, 2025
Open model documentation ↗
OpenAI: GPT-4o (2024-05-13)⌄Openai$5$150%—
MODEL PROFILE

OpenAI: GPT-4o (2024-05-13)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
4.1K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
17 supported
Model ID
openai/gpt-4o-2024-05-13
Published
May 13, 2024
Open model documentation ↗
OpenAI: GPT-4 Turbo (batch)⌄OpenaiBatch$5$150%—
MODEL PROFILE

OpenAI: GPT-4 Turbo (batch)

API profile based on provider metadata: image input, ai agents & tools, structured output.

Image inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
4.1K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-4-turbo:batch
Published
Apr 9, 2024
Open model documentation ↗
MoonshotAI: Kimi K3 (batch)⌄MoonshotaiBatch$3$150%—
MODEL PROFILE

MoonshotAI: Kimi K3 (batch)

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
moonshotai/kimi-k3:batch
Published
Jul 16, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 4.6⌄Anthropic$3$150%—
MODEL PROFILE

Anthropic: Claude Sonnet 4.6

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
anthropic/claude-sonnet-4.6
Published
Feb 17, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 4.5⌄Anthropic$3$150%—
MODEL PROFILE

Anthropic: Claude Sonnet 4.5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
64K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-sonnet-4.5
Published
Sep 29, 2025
Open model documentation ↗
Anthropic: Claude Sonnet 4⌄Anthropic$3$150%—
MODEL PROFILE

Anthropic: Claude Sonnet 4

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisLong contextLong responses
Context window
1M tokens
Maximum output
64K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
anthropic/claude-sonnet-4
Published
May 22, 2025
Open model documentation ↗
OpenAI: GPT-5.5 (batch)⌄OpenaiBatch$2.5$150%—
MODEL PROFILE

OpenAI: GPT-5.5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.5:batch
Published
Apr 24, 2026
Open model documentation ↗
OpenAI: GPT-5.4⌄Openai$2.5$150%—
MODEL PROFILE

OpenAI: GPT-5.4

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.4
Published
Mar 5, 2026
Open model documentation ↗
MoonshotAI: Kimi K3⌄Moonshotai$2.6481$13.28270%—
MODEL PROFILE

MoonshotAI: Kimi K3

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
moonshotai/kimi-k3
Published
Jul 16, 2026
Open model documentation ↗
OpenAI: GPT-5.3-Codex⌄Openai$1.75$140%—
MODEL PROFILE

OpenAI: GPT-5.3-Codex

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.3-codex
Published
Feb 24, 2026
Open model documentation ↗
OpenAI: GPT-5.2-Codex⌄Openai$1.75$140%—
MODEL PROFILE

OpenAI: GPT-5.2-Codex

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
openai/gpt-5.2-codex
Published
Jan 14, 2026
Open model documentation ↗
OpenAI: GPT-5.2 Chat⌄Openai$1.75$140%—
MODEL PROFILE

OpenAI: GPT-5.2 Chat

API profile based on provider metadata: image input, file input, coding, ai agents & tools, structured output, long responses.

Image inputFile inputCodingAI agents & toolsStructured outputLong responses
Context window
128K tokens
Maximum output
32K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Not declared
API features
6 supported
Model ID
openai/gpt-5.2-chat
Published
Dec 10, 2025
Open model documentation ↗
OpenAI: GPT-5.2⌄Openai$1.75$140%—
MODEL PROFILE

OpenAI: GPT-5.2

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.2
Published
Dec 10, 2025
Open model documentation ↗
Claude Opus 5 (batch)⌄AnthropicBatch$2.5$12.50%—
MODEL PROFILE

Claude Opus 5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-opus-5:batch
Published
Jul 24, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.8 (batch)⌄AnthropicBatch$2.5$12.50%—
MODEL PROFILE

Anthropic: Claude Opus 4.8 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-opus-4.8:batch
Published
May 27, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.7 (batch)⌄AnthropicBatch$2.5$12.50%—
MODEL PROFILE

Anthropic: Claude Opus 4.7 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-opus-4.7:batch
Published
Apr 16, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.6 (batch)⌄AnthropicBatch$2.5$12.50%—
MODEL PROFILE

Anthropic: Claude Opus 4.6 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-opus-4.6:batch
Published
Feb 4, 2026
Open model documentation ↗
Anthropic: Claude Opus 4.5 (batch)⌄AnthropicBatch$2.5$12.50%—
MODEL PROFILE

Anthropic: Claude Opus 4.5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
64K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-opus-4.5:batch
Published
Nov 24, 2025
Open model documentation ↗
OpenAI: GPT-5.6 Terra Pro⌄Openai$2$120%—
MODEL PROFILE

OpenAI: GPT-5.6 Terra Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-terra-pro
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Terra⌄Openai$2$120%—
MODEL PROFILE

OpenAI: GPT-5.6 Terra

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-terra
Published
Jul 9, 2026
Open model documentation ↗
Google: Nano Banana Pro (Gemini 3 Pro Image)⌄Google$2$120%—
MODEL PROFILE

Google: Nano Banana Pro (Gemini 3 Pro Image)

API profile based on provider metadata: image input, image generation, coding, ai agents & tools, complex analysis, structured output, long responses.

Image inputImage generationCodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-3-pro-image
Published
Jun 18, 2026
Open model documentation ↗
Google: Gemini 3.1 Pro Preview Custom Tools⌄GoogleFlagship$2$120%—
MODEL PROFILE

Google: Gemini 3.1 Pro Preview Custom Tools

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Audio, Images, Video, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-3.1-pro-preview-customtools
Published
Feb 25, 2026
Open model documentation ↗
Google: Gemini 3.1 Pro Preview⌄GoogleFlagship$2$120%—
MODEL PROFILE

Google: Gemini 3.1 Pro Preview

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Audio, Files, Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.1-pro-preview
Published
Feb 19, 2026
Open model documentation ↗
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)⌄Google$2$120%—
MODEL PROFILE

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

API profile based on provider metadata: image input, image generation, coding, complex analysis, structured output, long responses.

Image inputImage generationCodingComplex analysisStructured outputLong responses
Context window
65.5K tokens
Maximum output
32.8K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
9 supported
Model ID
google/gemini-3-pro-image-preview
Published
Nov 20, 2025
Open model documentation ↗
OpenAI: GPT Audio⌄Openai$2.5$100%—
MODEL PROFILE

OpenAI: GPT Audio

API profile based on provider metadata: audio, coding, ai agents & tools, structured output.

AudioCodingAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Audio
Produces
Text, Audio
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-audio
Published
Jan 20, 2026
Open model documentation ↗
OpenAI: GPT-4o (2024-11-20)⌄Openai$2.5$100%—
MODEL PROFILE

OpenAI: GPT-4o (2024-11-20)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
16 supported
Model ID
openai/gpt-4o-2024-11-20
Published
Nov 20, 2024
Open model documentation ↗
OpenAI: GPT-4o (2024-08-06)⌄Openai$2.5$100%—
MODEL PROFILE

OpenAI: GPT-4o (2024-08-06)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
17 supported
Model ID
openai/gpt-4o-2024-08-06
Published
Aug 6, 2024
Open model documentation ↗
OpenAI: GPT-4o⌄Openai$2.5$100%—
MODEL PROFILE

OpenAI: GPT-4o

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
17 supported
Model ID
openai/gpt-4o
Published
May 13, 2024
Open model documentation ↗
OpenAI: GPT-5.6 Sol Pro⌄Openai$2$100%—
MODEL PROFILE

OpenAI: GPT-5.6 Sol Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-sol-pro
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Sol⌄Openai$2$100%—
MODEL PROFILE

OpenAI: GPT-5.6 Sol

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-sol
Published
Jul 9, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 5⌄Anthropic$2$100%—
MODEL PROFILE

Anthropic: Claude Sonnet 5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
11 supported
Model ID
anthropic/claude-sonnet-5
Published
Jun 30, 2026
Open model documentation ↗
OpenAI: GPT-5.1-Codex-Max⌄Openai$1.25$100%—
MODEL PROFILE

OpenAI: GPT-5.1-Codex-Max

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
openai/gpt-5.1-codex-max
Published
Dec 4, 2025
Open model documentation ↗
OpenAI: GPT-5.1⌄Openai$1.25$100%—
MODEL PROFILE

OpenAI: GPT-5.1

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.1
Published
Nov 13, 2025
Open model documentation ↗
OpenAI: GPT-5.1-Codex⌄Openai$1.25$100%—
MODEL PROFILE

OpenAI: GPT-5.1-Codex

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
openai/gpt-5.1-codex
Published
Nov 13, 2025
Open model documentation ↗
OpenAI: GPT-5⌄Openai$1.25$100%—
MODEL PROFILE

OpenAI: GPT-5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5
Published
Aug 7, 2025
Open model documentation ↗
Google: Gemini 2.5 Pro⌄Google$1.25$100%—
MODEL PROFILE

Google: Gemini 2.5 Pro

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-pro
Published
Jun 17, 2025
Open model documentation ↗
Google: Gemini 2.5 Pro Preview 06-05⌄Google$1.25$100%—
MODEL PROFILE

Google: Gemini 2.5 Pro Preview 06-05

API profile based on provider metadata: image input, audio, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Files, Images, Text, Audio
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-pro-preview
Published
Jun 5, 2025
Open model documentation ↗
Google: Gemini 2.5 Pro Preview 05-06⌄Google$1.25$100%—
MODEL PROFILE

Google: Gemini 2.5 Pro Preview 05-06

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-pro-preview-05-06
Published
May 7, 2025
Open model documentation ↗
Google: Gemini 3.5 Flash⌄Google$1.5$90%—
MODEL PROFILE

Google: Gemini 3.5 Flash

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.5-flash
Published
May 19, 2026
Open model documentation ↗
OpenAI: o3⌄Openai$2$80%—
MODEL PROFILE

OpenAI: o3

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o3
Published
Apr 16, 2025
Open model documentation ↗
OpenAI: GPT-4.1⌄Openai$2$80%—
MODEL PROFILE

OpenAI: GPT-4.1

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-4.1
Published
Apr 14, 2025
Open model documentation ↗
Mistral: Mistral Medium 3.5⌄Mistralai$1.5$7.50%—
MODEL PROFILE

Mistral: Mistral Medium 3.5

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
mistralai/mistral-medium-3-5
Published
Apr 30, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 4.6 (batch)⌄AnthropicBatch$1.5$7.50%—
MODEL PROFILE

Anthropic: Claude Sonnet 4.6 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-sonnet-4.6:batch
Published
Feb 17, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 4.5 (batch)⌄AnthropicBatch$1.5$7.50%—
MODEL PROFILE

Anthropic: Claude Sonnet 4.5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
64K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
11 supported
Model ID
anthropic/claude-sonnet-4.5:batch
Published
Sep 29, 2025
Open model documentation ↗
OpenAI: GPT-5.4 (batch)⌄OpenaiBatch$1.25$7.50%—
MODEL PROFILE

OpenAI: GPT-5.4 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.4:batch
Published
Mar 5, 2026
Open model documentation ↗
Qwen: Qwen3.8 Max (0902)⌄Qwen$2$60%—
MODEL PROFILE

Qwen: Qwen3.8 Max (0902)

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3.8-max-0902
Published
Sep 4, 2026
Open model documentation ↗
Qwen: Qwen3.8 2.4T A95B⌄Qwen$2$60%—
MODEL PROFILE

Qwen: Qwen3.8 2.4T A95B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
qwen/qwen3.8-2.4t-a95b
Published
Aug 12, 2026
Open model documentation ↗
Qwen: Qwen3.8 2.4T A95B (batch)⌄QwenBatch$2$60%—
MODEL PROFILE

Qwen: Qwen3.8 2.4T A95B (batch)

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
909K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.8-2.4t-a95b:batch
Published
Aug 12, 2026
Open model documentation ↗
SpaceXAI: Grok 4.6⌄X-ai$2$60%—
MODEL PROFILE

SpaceXAI: Grok 4.6

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
500K tokens
Maximum output
450K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
x-ai/grok-4.6
Published
Aug 12, 2026
Open model documentation ↗
SpaceXAI: Grok 4.5⌄X-ai$2$60%—
MODEL PROFILE

SpaceXAI: Grok 4.5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
500K tokens
Maximum output
450K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
x-ai/grok-4.5
Published
Jul 8, 2026
Open model documentation ↗
Mistral Large 2407⌄Mistralai$2$60%—
MODEL PROFILE

Mistral Large 2407

API profile based on provider metadata: file input, ai agents & tools, structured output, long responses.

File inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
104.9K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-large-2407
Published
Nov 19, 2024
Open model documentation ↗
Mistral: Mixtral 8x22B Instruct⌄Mistralai$2$60%—
MODEL PROFILE

Mistral: Mixtral 8x22B Instruct

API profile based on provider metadata: file input, ai agents & tools, structured output, long responses.

File inputAI agents & toolsStructured outputLong responses
Context window
65.5K tokens
Maximum output
52.4K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mixtral-8x22b-instruct
Published
Apr 17, 2024
Open model documentation ↗
Mistral Large⌄Mistralai$2$60%—
MODEL PROFILE

Mistral Large

API profile based on provider metadata: file input, ai agents & tools, structured output, long responses.

File inputAI agents & toolsStructured outputLong responses
Context window
128K tokens
Maximum output
102.4K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-large
Published
Feb 26, 2024
Open model documentation ↗
OpenAI: GPT-5.2 (batch)⌄OpenaiBatch$0.875$70%—
MODEL PROFILE

OpenAI: GPT-5.2 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.2:batch
Published
Dec 10, 2025
Open model documentation ↗
Qwen: Qwen3.6 Max Preview⌄Qwen$1.027$6.1620%—
MODEL PROFILE

Qwen: Qwen3.6 Max Preview

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.6-max-preview
Published
Apr 27, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Terra Pro (batch)⌄OpenaiBatch$1$60%—
MODEL PROFILE

OpenAI: GPT-5.6 Terra Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-terra-pro:batch
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Terra (batch)⌄OpenaiBatch$1$60%—
MODEL PROFILE

OpenAI: GPT-5.6 Terra (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-terra:batch
Published
Jul 9, 2026
Open model documentation ↗
Google: Gemini 3.1 Pro Preview (batch)⌄GoogleBatch$1$60%—
MODEL PROFILE

Google: Gemini 3.1 Pro Preview (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Audio, Files, Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.1-pro-preview:batch
Published
Feb 19, 2026
Open model documentation ↗
OpenAI: GPT-3.5 Turbo 16k⌄OpenaiLegacy$3$40%—
MODEL PROFILE

OpenAI: GPT-3.5 Turbo 16k

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
16.4K tokens
Maximum output
4.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
15 supported
Model ID
openai/gpt-3.5-turbo-16k
Published
Aug 28, 2023
Open model documentation ↗
OpenAI: GPT-4o (batch)⌄OpenaiBatch$1.25$50%—
MODEL PROFILE

OpenAI: GPT-4o (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
16 supported
Model ID
openai/gpt-4o:batch
Published
May 13, 2024
Open model documentation ↗
OpenAI: GPT-5.6 Sol Pro (batch)⌄OpenaiBatch$1$50%—
MODEL PROFILE

OpenAI: GPT-5.6 Sol Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-sol-pro:batch
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Sol (batch)⌄OpenaiBatch$1$50%—
MODEL PROFILE

OpenAI: GPT-5.6 Sol (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-sol:batch
Published
Jul 9, 2026
Open model documentation ↗
Anthropic: Claude Sonnet 5 (batch)⌄AnthropicBatch$1$50%—
MODEL PROFILE

Anthropic: Claude Sonnet 5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
anthropic/claude-sonnet-5:batch
Published
Jun 30, 2026
Open model documentation ↗
Anthropic: Claude Haiku 4.5⌄Anthropic$1$50%—
MODEL PROFILE

Anthropic: Claude Haiku 4.5

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
64K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
anthropic/claude-haiku-4.5
Published
Oct 15, 2025
Open model documentation ↗
Qwen: Qwen3.7 Max⌄Qwen$1.475$4.4250%—
MODEL PROFILE

Qwen: Qwen3.7 Max

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.7-max
Published
May 21, 2026
Open model documentation ↗
OpenAI: GPT-5.1 (batch)⌄OpenaiBatch$0.625$50%—
MODEL PROFILE

OpenAI: GPT-5.1 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.1:batch
Published
Nov 13, 2025
Open model documentation ↗
OpenAI: GPT-5 (batch)⌄OpenaiBatch$0.625$50%—
MODEL PROFILE

OpenAI: GPT-5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5:batch
Published
Aug 7, 2025
Open model documentation ↗
Google: Gemini 2.5 Pro (batch)⌄GoogleBatch$0.625$50%—
MODEL PROFILE

Google: Gemini 2.5 Pro (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-pro:batch
Published
Jun 17, 2025
Open model documentation ↗
OpenAI: o4 Mini High⌄Openai$1.1$4.40%—
MODEL PROFILE

OpenAI: o4 Mini High

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/o4-mini-high
Published
Apr 16, 2025
Open model documentation ↗
OpenAI: o4 Mini⌄Openai$1.1$4.40%—
MODEL PROFILE

OpenAI: o4 Mini

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o4-mini
Published
Apr 16, 2025
Open model documentation ↗
OpenAI: o3 Mini High⌄Openai$1.1$4.40%—
MODEL PROFILE

OpenAI: o3 Mini High

API profile based on provider metadata: file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/o3-mini-high
Published
Feb 12, 2025
Open model documentation ↗
OpenAI: o3 Mini⌄Openai$1.1$4.40%—
MODEL PROFILE

OpenAI: o3 Mini

API profile based on provider metadata: file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o3-mini
Published
Jan 31, 2025
Open model documentation ↗
Google: Gemini 3.5 Flash (batch)⌄GoogleBatch$0.75$4.50%—
MODEL PROFILE

Google: Gemini 3.5 Flash (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.5-flash:batch
Published
May 19, 2026
Open model documentation ↗
OpenAI: GPT-5.4 Mini⌄Openai$0.75$4.50%—
MODEL PROFILE

OpenAI: GPT-5.4 Mini

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.4-mini
Published
Mar 17, 2026
Open model documentation ↗
OpenAI: o3 (batch)⌄OpenaiBatch$1$40%—
MODEL PROFILE

OpenAI: o3 (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o3:batch
Published
Apr 16, 2025
Open model documentation ↗
OpenAI: GPT-4.1 (batch)⌄OpenaiBatch$1$40%—
MODEL PROFILE

OpenAI: GPT-4.1 (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/gpt-4.1:batch
Published
Apr 14, 2025
Open model documentation ↗
MoonshotAI: Kimi K2.6⌄Moonshotai$0.95$40%—
MODEL PROFILE

MoonshotAI: Kimi K2.6

API profile based on provider metadata: image input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
moonshotai/kimi-k2.6
Published
Apr 20, 2026
Open model documentation ↗
DeepSeek: DeepSeek V4 Pro 0423⌄Deepseek$1.6$3.20%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Pro 0423

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
393.2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
21 supported
Model ID
deepseek/deepseek-v4-pro
Published
Apr 24, 2026
Open model documentation ↗
Qwen: Qwen3 Max Thinking⌄Qwen$0.78$3.90%—
MODEL PROFILE

Qwen: Qwen3 Max Thinking

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-max-thinking
Published
Feb 9, 2026
Open model documentation ↗
Qwen: Qwen3 Max⌄Qwen$0.78$3.90%—
MODEL PROFILE

Qwen: Qwen3 Max

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen3-max
Published
Sep 24, 2025
Open model documentation ↗
Google: Gemini 3.8 Flash⌄Google$0.75$3.750%—
MODEL PROFILE

Google: Gemini 3.8 Flash

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.8-flash
Published
Sep 2, 2026
Open model documentation ↗
Google: Gemini 3.7 Flash⌄Google$0.75$3.750%—
MODEL PROFILE

Google: Gemini 3.7 Flash

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.7-flash
Published
Aug 13, 2026
Open model documentation ↗
Google: Gemini 3.6 Flash⌄Google$0.75$3.750%—
MODEL PROFILE

Google: Gemini 3.6 Flash

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.6-flash
Published
Jul 21, 2026
Open model documentation ↗
Mistral: Mistral Medium 3.5 (batch)⌄MistralaiBatch$0.75$3.750%—
MODEL PROFILE

Mistral: Mistral Medium 3.5 (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
mistralai/mistral-medium-3-5:batch
Published
Apr 30, 2026
Open model documentation ↗
OpenAI: GPT-5 Image Mini⌄Openai$2.5$20%—
MODEL PROFILE

OpenAI: GPT-5 Image Mini

API profile based on provider metadata: image input, file input, image generation, coding, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputImage generationCodingComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Images, Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-5-image-mini
Published
Oct 16, 2025
Open model documentation ↗
Qwen: Qwen3 VL 235B A22B Thinking⌄Qwen$0.4$40%—
MODEL PROFILE

Qwen: Qwen3 VL 235B A22B Thinking

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long responses.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
32.8K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-vl-235b-a22b-thinking
Published
Sep 24, 2025
Open model documentation ↗
MoonshotAI: Kimi K2.7 Code⌄Moonshotai$0.71$3.50%—
MODEL PROFILE

MoonshotAI: Kimi K2.7 Code

API profile based on provider metadata: image input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
moonshotai/kimi-k2.7-code
Published
Jun 12, 2026
Open model documentation ↗
Qwen: Qwen3.5 397B A17B⌄Qwen$0.55$3.50%—
MODEL PROFILE

Qwen: Qwen3.5 397B A17B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.5-397b-a17b
Published
Feb 16, 2026
Open model documentation ↗
Qwen: Qwen3 Coder Plus⌄Qwen$0.65$3.250%—
MODEL PROFILE

Qwen: Qwen3 Coder Plus

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen3-coder-plus
Published
Sep 24, 2025
Open model documentation ↗
SpaceXAI: Grok 4.3⌄X-ai$1.25$2.50%—
MODEL PROFILE

SpaceXAI: Grok 4.3

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
900K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
x-ai/grok-4.3
Published
May 1, 2026
Open model documentation ↗
SpaceXAI: Grok 4.20 Multi-Agent⌄X-ai$1.25$2.50%—
MODEL PROFILE

SpaceXAI: Grok 4.20 Multi-Agent

API profile based on provider metadata: image input, file input, coding, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingComplex analysisStructured outputLong contextLong responses
Context window
2M tokens
Maximum output
1.8M tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
x-ai/grok-4.20-multi-agent
Published
Mar 31, 2026
Open model documentation ↗
SpaceXAI: Grok 4.20⌄X-ai$1.25$2.50%—
MODEL PROFILE

SpaceXAI: Grok 4.20

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
2M tokens
Maximum output
1.8M tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
x-ai/grok-4.20
Published
Mar 31, 2026
Open model documentation ↗
Google: Nano Banana 2 (Gemini 3.1 Flash Image)⌄Google$0.5$30%—
MODEL PROFILE

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

API profile based on provider metadata: image input, image generation, coding, complex analysis, structured output, long responses.

Image inputImage generationCodingComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
9 supported
Model ID
google/gemini-3.1-flash-image
Published
Jun 18, 2026
Open model documentation ↗
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)⌄Google$0.5$30%—
MODEL PROFILE

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)

API profile based on provider metadata: image input, image generation, coding, complex analysis, structured output, long responses.

Image inputImage generationCodingComplex analysisStructured outputLong responses
Context window
65.5K tokens
Maximum output
59K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
9 supported
Model ID
google/gemini-3.1-flash-image-preview
Published
Feb 26, 2026
Open model documentation ↗
Google: Gemini 3 Flash Preview⌄Google$0.5$30%—
MODEL PROFILE

Google: Gemini 3 Flash Preview

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3-flash-preview
Published
Dec 17, 2025
Open model documentation ↗
OpenAI: GPT-3.5 Turbo Instruct⌄OpenaiLegacy$1.5$20%—
MODEL PROFILE

OpenAI: GPT-3.5 Turbo Instruct

API profile based on provider metadata: structured output.

Structured output
Context window
4.1K tokens
Maximum output
3.7K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
12 supported
Model ID
openai/gpt-3.5-turbo-instruct
Published
Sep 28, 2023
Open model documentation ↗
DeepSeek: R1⌄Deepseek$0.7$2.50%—
MODEL PROFILE

DeepSeek: R1

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
64K tokens
Maximum output
16K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
deepseek/deepseek-r1
Published
Jan 20, 2025
Open model documentation ↗
MoonshotAI: Kimi K2 Thinking⌄Moonshotai$0.6$2.50%—
MODEL PROFILE

MoonshotAI: Kimi K2 Thinking

API profile based on provider metadata: ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

AI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
100.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
moonshotai/kimi-k2-thinking
Published
Nov 6, 2025
Open model documentation ↗
MoonshotAI: Kimi K2 0905⌄Moonshotai$0.6$2.50%—
MODEL PROFILE

MoonshotAI: Kimi K2 0905

API profile based on provider metadata: ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

AI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
100.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
moonshotai/kimi-k2-0905
Published
Sep 5, 2025
Open model documentation ↗
SpaceXAI: Grok Build 0.1⌄X-ai$1$20%—
MODEL PROFILE

SpaceXAI: Grok Build 0.1

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
256K tokens
Maximum output
230.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
x-ai/grok-build-0.1
Published
May 20, 2026
Open model documentation ↗
SpaceXAI: Grok 4.3 (batch)⌄X-aiBatch$1$20%—
MODEL PROFILE

SpaceXAI: Grok 4.3 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
900K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
x-ai/grok-4.3:batch
Published
May 1, 2026
Open model documentation ↗
OpenAI: GPT Audio Mini⌄Openai$0.6$2.40%—
MODEL PROFILE

OpenAI: GPT Audio Mini

API profile based on provider metadata: audio, coding, ai agents & tools, structured output.

AudioCodingAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Audio
Produces
Text, Audio
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-audio-mini
Published
Jan 19, 2026
Open model documentation ↗
Anthropic: Claude Haiku 4.5 (batch)⌄AnthropicBatch$0.5$2.50%—
MODEL PROFILE

Anthropic: Claude Haiku 4.5 (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
64K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
11 supported
Model ID
anthropic/claude-haiku-4.5:batch
Published
Oct 15, 2025
Open model documentation ↗
OpenAI: GPT-3.5 Turbo (older v0613)⌄OpenaiLegacy$1$20%—
MODEL PROFILE

OpenAI: GPT-3.5 Turbo (older v0613)

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
4.1K tokens
Maximum output
3.7K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
openai/gpt-3.5-turbo-0613
Published
Jan 25, 2024
Open model documentation ↗
MoonshotAI: Kimi K2 0711⌄Moonshotai$0.57$2.30%—
MODEL PROFILE

MoonshotAI: Kimi K2 0711

API profile based on provider metadata: ai agents & tools, long responses.

AI agents & toolsLong responses
Context window
131.1K tokens
Maximum output
100.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
moonshotai/kimi-k2
Published
Jul 11, 2025
Open model documentation ↗
Google: Gemini 3.5 Flash Lite⌄Google$0.3$2.50%—
MODEL PROFILE

Google: Gemini 3.5 Flash Lite

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.5-flash-lite
Published
Jul 21, 2026
Open model documentation ↗
Google: Nano Banana (Gemini 2.5 Flash Image)⌄Google$0.3$2.50%—
MODEL PROFILE

Google: Nano Banana (Gemini 2.5 Flash Image)

API profile based on provider metadata: image input, image generation, coding, structured output.

Image inputImage generationCodingStructured output
Context window
32.8K tokens
Maximum output
8.2K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
7 supported
Model ID
google/gemini-2.5-flash-image
Published
Oct 7, 2025
Open model documentation ↗
Google: Gemini 2.5 Flash⌄Google$0.3$2.50%—
MODEL PROFILE

Google: Gemini 2.5 Flash

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Files, Images, Text, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-flash
Published
Jun 17, 2025
Open model documentation ↗
Qwen: Qwen3.8 27B⌄Qwen$0.214$2.550%—
MODEL PROFILE

Qwen: Qwen3.8 27B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
21 supported
Model ID
qwen/qwen3.8-27b
Published
Aug 14, 2026
Open model documentation ↗
OpenAI: o4 Mini (batch)⌄OpenaiBatch$0.55$2.20%—
MODEL PROFILE

OpenAI: o4 Mini (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o4-mini:batch
Published
Apr 16, 2025
Open model documentation ↗
OpenAI: o3 Mini (batch)⌄OpenaiBatch$0.55$2.20%—
MODEL PROFILE

OpenAI: o3 Mini (batch)

API profile based on provider metadata: file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
200K tokens
Maximum output
100K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/o3-mini:batch
Published
Jan 31, 2025
Open model documentation ↗
MoonshotAI: Kimi K2.5⌄Moonshotai$0.45$2.250%—
MODEL PROFILE

MoonshotAI: Kimi K2.5

API profile based on provider metadata: image input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
moonshotai/kimi-k2.5
Published
Jan 27, 2026
Open model documentation ↗
DeepSeek: R1 0528⌄Deepseek$0.5$2.150%—
MODEL PROFILE

DeepSeek: R1 0528

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
163.8K tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-r1-0528
Published
May 28, 2025
Open model documentation ↗
DeepSeek: DeepSeek V4 Pro 0813 (batch)⌄DeepseekBatch$0.66$1.980%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Pro 0813 (batch)

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-v4-pro-0813:batch
Published
Aug 12, 2026
Open model documentation ↗
OpenAI: GPT-5.4 Mini (batch)⌄OpenaiBatch$0.375$2.250%—
MODEL PROFILE

OpenAI: GPT-5.4 Mini (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.4-mini:batch
Published
Mar 17, 2026
Open model documentation ↗
Qwen: Qwen3 VL 30B A3B Thinking⌄Qwen$0.2$2.40%—
MODEL PROFILE

Qwen: Qwen3 VL 30B A3B Thinking

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32.8K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-vl-30b-a3b-thinking
Published
Oct 7, 2025
Open model documentation ↗
Qwen: Qwen3 30B A3B Thinking 2507⌄Qwen$0.2$2.40%—
MODEL PROFILE

Qwen: Qwen3 30B A3B Thinking 2507

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
81.9K tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
qwen/qwen3-30b-a3b-thinking-2507
Published
Aug 28, 2025
Open model documentation ↗
Qwen: Qwen3 235B A22B Thinking 2507⌄Qwen$0.23$2.30%—
MODEL PROFILE

Qwen: Qwen3 235B A22B Thinking 2507

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-235b-a22b-thinking-2507
Published
Jul 25, 2025
Open model documentation ↗
Mistral: Devstral 2 2512⌄Mistralai$0.4$20%—
MODEL PROFILE

Mistral: Devstral 2 2512

API profile based on provider metadata: file input, coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/devstral-2512
Published
Dec 9, 2025
Open model documentation ↗
Mistral: Mistral Medium 3.1⌄Mistralai$0.4$20%—
MODEL PROFILE

Mistral: Mistral Medium 3.1

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long responses.

Image inputFile inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
104.9K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-medium-3.1
Published
Aug 13, 2025
Open model documentation ↗
Mistral: Mistral Medium 3⌄Mistralai$0.4$20%—
MODEL PROFILE

Mistral: Mistral Medium 3

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long responses.

Image inputFile inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
104.9K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-medium-3
Published
May 7, 2025
Open model documentation ↗
Qwen: Qwen3.5-122B-A10B⌄Qwen$0.26$2.080%—
MODEL PROFILE

Qwen: Qwen3.5-122B-A10B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.5-122b-a10b
Published
Feb 25, 2026
Open model documentation ↗
DeepSeek: DeepSeek V4 Pro 0813⌄Deepseek$0.5782$1.73450%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Pro 0813

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
393.2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
deepseek/deepseek-v4-pro-0813
Published
Aug 12, 2026
Open model documentation ↗
Qwen: Qwen3.6 27B⌄Qwen$0.3$20%—
MODEL PROFILE

Qwen: Qwen3.6 27B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.6-27b
Published
Apr 27, 2026
Open model documentation ↗
Qwen: Qwen3 VL 8B Thinking⌄Qwen$0.18$2.10%—
MODEL PROFILE

Qwen: Qwen3 VL 8B Thinking

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long responses.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-vl-8b-thinking
Published
Oct 14, 2025
Open model documentation ↗
Qwen: Qwen3.6 Plus⌄Qwen$0.325$1.950%—
MODEL PROFILE

Qwen: Qwen3.6 Plus

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.6-plus
Published
Apr 2, 2026
Open model documentation ↗
Qwen: Qwen3 235B A22B⌄Qwen$0.455$1.820%—
MODEL PROFILE

Qwen: Qwen3 235B A22B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
131.1K tokens
Maximum output
8.2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
qwen/qwen3-235b-a22b
Published
Apr 29, 2025
Open model documentation ↗
Google: Gemini 3.8 Flash (batch)⌄GoogleBatch$0.375$1.8750%—
MODEL PROFILE

Google: Gemini 3.8 Flash (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
google/gemini-3.8-flash:batch
Published
Sep 2, 2026
Open model documentation ↗
Google: Gemini 3.7 Flash (batch)⌄GoogleBatch$0.375$1.8750%—
MODEL PROFILE

Google: Gemini 3.7 Flash (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
google/gemini-3.7-flash:batch
Published
Aug 13, 2026
Open model documentation ↗
Google: Gemini 3.6 Flash (batch)⌄GoogleBatch$0.375$1.8750%—
MODEL PROFILE

Google: Gemini 3.6 Flash (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
google/gemini-3.6-flash:batch
Published
Jul 21, 2026
Open model documentation ↗
OpenAI: GPT-5.1-Codex-Mini⌄Openai$0.25$20%—
MODEL PROFILE

OpenAI: GPT-5.1-Codex-Mini

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Images, Text
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
openai/gpt-5.1-codex-mini
Published
Nov 13, 2025
Open model documentation ↗
OpenAI: GPT-5 Mini⌄Openai$0.25$20%—
MODEL PROFILE

OpenAI: GPT-5 Mini

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5-mini
Published
Aug 7, 2025
Open model documentation ↗
Qwen: Qwen3 VL 235B A22B Instruct⌄Qwen$0.21$1.90%—
MODEL PROFILE

Qwen: Qwen3 VL 235B A22B Instruct

API profile based on provider metadata: image input, coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32.8K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-vl-235b-a22b-instruct
Published
Sep 24, 2025
Open model documentation ↗
Qwen: Qwen3.5 Plus 2026-04-20⌄Qwen$0.3$1.80%—
MODEL PROFILE

Qwen: Qwen3.5 Plus 2026-04-20

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.5-plus-20260420
Published
Apr 27, 2026
Open model documentation ↗
Mistral: Mistral Large 3 2512⌄Mistralai$0.5$1.50%—
MODEL PROFILE

Mistral: Mistral Large 3 2512

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-large-2512
Published
Dec 1, 2025
Open model documentation ↗
OpenAI: GPT-3.5 Turbo⌄OpenaiLegacy$0.5$1.50%—
MODEL PROFILE

OpenAI: GPT-3.5 Turbo

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
16.4K tokens
Maximum output
4.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-3.5-turbo
Published
May 28, 2023
Open model documentation ↗
OpenAI: GPT-4.1 Mini⌄Openai$0.4$1.60%—
MODEL PROFILE

OpenAI: GPT-4.1 Mini

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-4.1-mini
Published
Apr 14, 2025
Open model documentation ↗
Qwen: Qwen3.5 Plus 2026-02-15⌄Qwen$0.26$1.560%—
MODEL PROFILE

Qwen: Qwen3.5 Plus 2026-02-15

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.5-plus-02-15
Published
Feb 16, 2026
Open model documentation ↗
Qwen: Qwen2.5 VL 72B Instruct⌄Qwen$0.8$10%—
MODEL PROFILE

Qwen: Qwen2.5 VL 72B Instruct

API profile based on provider metadata: image input, coding, structured output, long responses.

Image inputCodingStructured outputLong responses
Context window
128K tokens
Maximum output
115.2K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen2.5-vl-72b-instruct
Published
Feb 1, 2025
Open model documentation ↗
Qwen: Qwen3.5-27B⌄Qwen$0.195$1.560%—
MODEL PROFILE

Qwen: Qwen3.5-27B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.5-27b
Published
Feb 25, 2026
Open model documentation ↗
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)⌄Google$0.25$1.50%—
MODEL PROFILE

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

API profile based on provider metadata: image input, image generation, coding, complex analysis, structured output, long responses.

Image inputImage generationCodingComplex analysisStructured outputLong responses
Context window
65.5K tokens
Maximum output
59K tokens
Accepts
Images, Text
Produces
Images, Text
Safety moderation
Not declared
API features
8 supported
Model ID
google/gemini-3.1-flash-lite-image
Published
Jun 30, 2026
Open model documentation ↗
Google: Gemini 3.1 Flash Lite⌄Google$0.25$1.50%—
MODEL PROFILE

Google: Gemini 3.1 Flash Lite

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.1-flash-lite
Published
May 7, 2026
Open model documentation ↗
Google: Gemini 3.1 Flash Lite Preview⌄Google$0.25$1.50%—
MODEL PROFILE

Google: Gemini 3.1 Flash Lite Preview

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-3.1-flash-lite-preview
Published
Mar 3, 2026
Open model documentation ↗
Google: Gemini 3 Flash Preview (batch)⌄GoogleBatch$0.25$1.50%—
MODEL PROFILE

Google: Gemini 3 Flash Preview (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3-flash-preview:batch
Published
Dec 17, 2025
Open model documentation ↗
Qwen2.5 Coder 32B Instruct⌄Qwen$0.66$10%—
MODEL PROFILE

Qwen2.5 Coder 32B Instruct

API profile based on provider metadata: coding.

Coding
Context window
32.8K tokens
Maximum output
29.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
qwen/qwen-2.5-coder-32b-instruct
Published
Nov 12, 2024
Open model documentation ↗
Qwen: Qwen3.7 Plus⌄Qwen$0.32$1.280%—
MODEL PROFILE

Qwen: Qwen3.7 Plus

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.7-plus
Published
Jun 3, 2026
Open model documentation ↗
DeepSeek: R1 Distill Llama 70B⌄Deepseek$0.8$0.80%—
MODEL PROFILE

DeepSeek: R1 Distill Llama 70B

API profile based on provider metadata: coding, complex analysis.

CodingComplex analysis
Context window
8.2K tokens
Maximum output
7.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
deepseek/deepseek-r1-distill-llama-70b
Published
Jan 23, 2025
Open model documentation ↗
Qwen: Qwen3.5-35B-A3B⌄Qwen$0.3125$1.250%—
MODEL PROFILE

Qwen: Qwen3.5-35B-A3B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong context
Context window
262.1K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.5-35b-a3b
Published
Feb 25, 2026
Open model documentation ↗
Anthropic: Claude 3 Haiku⌄Anthropic$0.25$1.250%—
MODEL PROFILE

Anthropic: Claude 3 Haiku

API profile based on provider metadata: image input, coding, ai agents & tools, long context. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsLong context
Context window
200K tokens
Maximum output
4.1K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Enabled
API features
7 supported
Model ID
anthropic/claude-3-haiku
Published
Mar 13, 2024
Open model documentation ↗
OpenAI: GPT-5.4 Nano⌄Openai$0.2$1.250%—
MODEL PROFILE

OpenAI: GPT-5.4 Nano

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.4-nano
Published
Mar 17, 2026
Open model documentation ↗
Google: Gemini 3.5 Flash Lite (batch)⌄GoogleBatch$0.15$1.250%—
MODEL PROFILE

Google: Gemini 3.5 Flash Lite (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
google/gemini-3.5-flash-lite:batch
Published
Jul 21, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Luna Pro⌄Openai$0.2$1.20%—
MODEL PROFILE

OpenAI: GPT-5.6 Luna Pro

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-luna-pro
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Luna⌄Openai$0.2$1.20%—
MODEL PROFILE

OpenAI: GPT-5.6 Luna

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5.6-luna
Published
Jul 9, 2026
Open model documentation ↗
Google: Gemini 2.5 Flash (batch)⌄GoogleBatch$0.15$1.250%—
MODEL PROFILE

Google: Gemini 2.5 Flash (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Files, Images, Text, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-flash:batch
Published
Jun 17, 2025
Open model documentation ↗
Google: Gemma 4 31B (batch)⌄GoogleBatch$0.39$0.970%—
MODEL PROFILE

Google: Gemma 4 31B (batch)

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
google/gemma-4-31b-it:batch
Published
Apr 2, 2026
Open model documentation ↗
Qwen: Qwen3 Next 80B A3B Thinking⌄Qwen$0.15$1.20%—
MODEL PROFILE

Qwen: Qwen3 Next 80B A3B Thinking

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-next-80b-a3b-thinking
Published
Sep 11, 2025
Open model documentation ↗
Qwen: Qwen3.6 Flash⌄Qwen$0.1875$1.1250%—
MODEL PROFILE

Qwen: Qwen3.6 Flash

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.6-flash
Published
Apr 27, 2026
Open model documentation ↗
Qwen: Qwen3 Coder 480B A35B⌄Qwen$0.3$10%—
MODEL PROFILE

Qwen: Qwen3 Coder 480B A35B

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-coder
Published
Jul 23, 2025
Open model documentation ↗
Google: Gemma 2 27B⌄Google$0.65$0.650%—
MODEL PROFILE

Google: Gemma 2 27B

API profile based on provider metadata: coding, structured output.

CodingStructured output
Context window
8.2K tokens
Maximum output
2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
10 supported
Model ID
google/gemma-2-27b-it
Published
Jul 13, 2024
Open model documentation ↗
DeepSeek: DeepSeek V3⌄Deepseek$0.2574$1.02870%—
MODEL PROFILE

DeepSeek: DeepSeek V3

API profile based on provider metadata: coding, ai agents & tools, structured output.

CodingAI agents & toolsStructured output
Context window
163.8K tokens
Maximum output
16K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
deepseek/deepseek-chat
Published
Dec 26, 2024
Open model documentation ↗
DeepSeek: DeepSeek V3.1 Terminus⌄Deepseek$0.27$10%—
MODEL PROFILE

DeepSeek: DeepSeek V3.1 Terminus

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
163.8K tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
deepseek/deepseek-v3.1-terminus
Published
Sep 22, 2025
Open model documentation ↗
DeepSeek: DeepSeek V3 0324⌄Deepseek$0.25$10%—
MODEL PROFILE

DeepSeek: DeepSeek V3 0324

API profile based on provider metadata: coding, ai agents & tools, structured output, long responses.

CodingAI agents & toolsStructured outputLong responses
Context window
163.8K tokens
Maximum output
147.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
deepseek/deepseek-chat-v3-0324
Published
Mar 24, 2025
Open model documentation ↗
DeepSeek: DeepSeek V3.1⌄Deepseek$0.25$0.950%—
MODEL PROFILE

DeepSeek: DeepSeek V3.1

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
163.8K tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-chat-v3.1
Published
Aug 21, 2025
Open model documentation ↗
Mistral: Mistral Medium 3.1 (batch)⌄MistralaiBatch$0.2$10%—
MODEL PROFILE

Mistral: Mistral Medium 3.1 (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long responses.

Image inputFile inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
104.9K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-medium-3.1:batch
Published
Aug 13, 2025
Open model documentation ↗
Mistral: Codestral 2508⌄Mistralai$0.3$0.90%—
MODEL PROFILE

Mistral: Codestral 2508

API profile based on provider metadata: file input, coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsStructured outputLong contextLong responses
Context window
256K tokens
Maximum output
204.8K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
mistralai/codestral-2508
Published
Aug 1, 2025
Open model documentation ↗
Qwen: Qwen3 Next 80B A3B Instruct⌄Qwen$0.09$1.10%—
MODEL PROFILE

Qwen: Qwen3 Next 80B A3B Instruct

API profile based on provider metadata: coding, ai agents & tools, structured output, long context. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong context
Context window
262.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-next-80b-a3b-instruct
Published
Sep 11, 2025
Open model documentation ↗
Qwen: Qwen3 Coder Flash⌄Qwen$0.195$0.9750%—
MODEL PROFILE

Qwen: Qwen3 Coder Flash

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
qwen/qwen3-coder-flash
Published
Sep 17, 2025
Open model documentation ↗
Qwen: Qwen3 14B⌄Qwen$0.2275$0.910%—
MODEL PROFILE

Qwen: Qwen3 14B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
131.1K tokens
Maximum output
8.2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3-14b
Published
Apr 29, 2025
Open model documentation ↗
OpenAI: GPT-5 Mini (batch)⌄OpenaiBatch$0.125$10%—
MODEL PROFILE

OpenAI: GPT-5 Mini (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5-mini:batch
Published
Aug 7, 2025
Open model documentation ↗
Qwen: Qwen Plus 0728⌄Qwen$0.26$0.780%—
MODEL PROFILE

Qwen: Qwen Plus 0728

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen-plus-2025-07-28
Published
Sep 8, 2025
Open model documentation ↗
Qwen: Qwen-Plus⌄Qwen$0.26$0.780%—
MODEL PROFILE

Qwen: Qwen-Plus

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen-plus
Published
Feb 1, 2025
Open model documentation ↗
Mistral: Mistral Large 3 2512 (batch)⌄MistralaiBatch$0.25$0.750%—
MODEL PROFILE

Mistral: Mistral Large 3 2512 (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-large-2512:batch
Published
Dec 1, 2025
Open model documentation ↗
OpenAI: GPT-3.5 Turbo (batch)⌄OpenaiBatchLegacy$0.25$0.750%—
MODEL PROFILE

OpenAI: GPT-3.5 Turbo (batch)

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
16.4K tokens
Maximum output
4.1K tokens
Accepts
Text
Produces
Text
Safety moderation
Enabled
API features
14 supported
Model ID
openai/gpt-3.5-turbo:batch
Published
May 28, 2023
Open model documentation ↗
Qwen: Qwen3.6 35B A3B⌄QwenGood value$0.1$0.90%—
MODEL PROFILE

Qwen: Qwen3.6 35B A3B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.6-35b-a3b
Published
Apr 27, 2026
Open model documentation ↗
OpenAI: GPT-4.1 Mini (batch)⌄OpenaiBatch$0.2$0.80%—
MODEL PROFILE

OpenAI: GPT-4.1 Mini (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/gpt-4.1-mini:batch
Published
Apr 14, 2025
Open model documentation ↗
Qwen: Qwen3 Coder Next⌄QwenGood value$0.12$0.80%—
MODEL PROFILE

Qwen: Qwen3 Coder Next

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-coder-next
Published
Feb 4, 2026
Open model documentation ↗
Mistral: Mistral Small 3.1 24B⌄MistralaiGood value$0.351$0.5550%—
MODEL PROFILE

Mistral: Mistral Small 3.1 24B

API profile based on provider metadata: image input, long responses.

Image inputLong responses
Context window
128K tokens
Maximum output
102.4K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
mistralai/mistral-small-3.1-24b-instruct
Published
Mar 17, 2025
Open model documentation ↗
Meta: Llama 4 Maverick⌄Meta-llamaGood value$0.2$0.6960%—
MODEL PROFILE

Meta: Llama 4 Maverick

API profile based on provider metadata: image input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
115.2K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
meta-llama/llama-4-maverick
Published
Apr 5, 2025
Open model documentation ↗
DeepSeek: DeepSeek V4 Flash Vision Exp⌄DeepseekGood value$0.22$0.660%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Flash Vision Exp

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
deepseek/deepseek-v4-flash-vision-exp
Published
Aug 21, 2026
Open model documentation ↗
Google: Gemini 3.1 Flash Lite (batch)⌄GoogleBatch$0.125$0.750%—
MODEL PROFILE

Google: Gemini 3.1 Flash Lite (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video, Files, Audio
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
google/gemini-3.1-flash-lite:batch
Published
May 7, 2026
Open model documentation ↗
Mistral: Saba⌄MistralaiGood value$0.2$0.60%—
MODEL PROFILE

Mistral: Saba

API profile based on provider metadata: file input, ai agents & tools, structured output.

File inputAI agents & toolsStructured output
Context window
32.8K tokens
Maximum output
26.2K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/mistral-saba
Published
Feb 17, 2025
Open model documentation ↗
Meta: Llama 3.1 70B Instruct⌄Meta-llamaGood value$0.4$0.40%—
MODEL PROFILE

Meta: Llama 3.1 70B Instruct

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
meta-llama/llama-3.1-70b-instruct
Published
Jul 23, 2024
Open model documentation ↗
Qwen2.5 72B Instruct⌄QwenGood value$0.36$0.40%—
MODEL PROFILE

Qwen2.5 72B Instruct

API profile based on provider metadata: coding, ai agents & tools, structured output.

CodingAI agents & toolsStructured output
Context window
32.8K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
qwen/qwen-2.5-72b-instruct
Published
Sep 19, 2024
Open model documentation ↗
DeepSeek: DeepSeek V4.1 Flash⌄DeepseekGood value$0.15$0.60%—
MODEL PROFILE

DeepSeek: DeepSeek V4.1 Flash

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
384K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
deepseek/deepseek-v4.1-flash
Published
Sep 10, 2026
Open model documentation ↗
Mistral: Mistral Small 4⌄MistralaiGood value$0.15$0.60%—
MODEL PROFILE

Mistral: Mistral Small 4

API profile based on provider metadata: image input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
mistralai/mistral-small-2603
Published
Mar 16, 2026
Open model documentation ↗
Qwen: Qwen3 VL 30B A3B Instruct⌄QwenGood value$0.15$0.60%—
MODEL PROFILE

Qwen: Qwen3 VL 30B A3B Instruct

API profile based on provider metadata: image input, coding, ai agents & tools, structured output, long context. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsStructured outputLong context
Context window
262.1K tokens
Maximum output
16.4K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-vl-30b-a3b-instruct
Published
Oct 7, 2025
Open model documentation ↗
OpenAI: gpt-oss-120b (batch)⌄OpenaiBatch$0.15$0.60%—
MODEL PROFILE

OpenAI: gpt-oss-120b (batch)

API profile based on provider metadata: ai agents & tools, complex analysis, structured output, long responses.

AI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
openai/gpt-oss-120b:batch
Published
Aug 5, 2025
Open model documentation ↗
OpenAI: GPT-4o-mini⌄OpenaiGood value$0.15$0.60%—
MODEL PROFILE

OpenAI: GPT-4o-mini

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
17 supported
Model ID
openai/gpt-4o-mini
Published
Jul 18, 2024
Open model documentation ↗
OpenAI: GPT-4o-mini (2024-07-18)⌄OpenaiGood value$0.15$0.60%—
MODEL PROFILE

OpenAI: GPT-4o-mini (2024-07-18)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
16 supported
Model ID
openai/gpt-4o-mini-2024-07-18
Published
Jul 18, 2024
Open model documentation ↗
OpenAI: GPT-5.4 Nano (batch)⌄OpenaiBatch$0.1$0.6250%—
MODEL PROFILE

OpenAI: GPT-5.4 Nano (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.4-nano:batch
Published
Mar 17, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Luna Pro (batch)⌄OpenaiBatch$0.1$0.60%—
MODEL PROFILE

OpenAI: GPT-5.6 Luna Pro (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-luna-pro:batch
Published
Jul 9, 2026
Open model documentation ↗
OpenAI: GPT-5.6 Luna (batch)⌄OpenaiBatch$0.1$0.60%—
MODEL PROFILE

OpenAI: GPT-5.6 Luna (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.1M tokens
Maximum output
128K tokens
Accepts
Files, Images, Text
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5.6-luna:batch
Published
Jul 9, 2026
Open model documentation ↗
DeepSeek: DeepSeek V3.2 Exp⌄DeepseekGood value$0.27$0.410%—
MODEL PROFILE

DeepSeek: DeepSeek V3.2 Exp

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
163.8K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-v3.2-exp
Published
Sep 29, 2025
Open model documentation ↗
DeepSeek: DeepSeek V3.2⌄DeepseekGood value$0.269$0.40%—
MODEL PROFILE

DeepSeek: DeepSeek V3.2

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long responses.

CodingAI agents & toolsComplex analysisStructured outputLong responses
Context window
163.8K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-v3.2
Published
Dec 1, 2025
Open model documentation ↗
Qwen: Qwen3.8 Flash⌄QwenGood value$0.15$0.470%—
MODEL PROFILE

Qwen: Qwen3.8 Flash

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
131.1K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.8-flash
Published
Aug 26, 2026
Open model documentation ↗
Qwen: Qwen3 30B A3B⌄QwenGood value$0.12$0.50%—
MODEL PROFILE

Qwen: Qwen3 30B A3B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-30b-a3b
Published
Apr 29, 2025
Open model documentation ↗
Mistral: Codestral 2508 (batch)⌄MistralaiBatch$0.15$0.450%—
MODEL PROFILE

Mistral: Codestral 2508 (batch)

API profile based on provider metadata: file input, coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

File inputCodingAI agents & toolsStructured outputLong contextLong responses
Context window
256K tokens
Maximum output
204.8K tokens
Accepts
Text, Files
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
mistralai/codestral-2508:batch
Published
Aug 1, 2025
Open model documentation ↗
Qwen: Qwen3 VL 8B Instruct⌄QwenGood value$0.117$0.4550%—
MODEL PROFILE

Qwen: Qwen3 VL 8B Instruct

API profile based on provider metadata: image input, coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-vl-8b-instruct
Published
Oct 14, 2025
Open model documentation ↗
Qwen: Qwen3 8B⌄QwenGood value$0.117$0.4550%—
MODEL PROFILE

Qwen: Qwen3 8B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
131.1K tokens
Maximum output
8.2K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
qwen/qwen3-8b
Published
Apr 29, 2025
Open model documentation ↗
Google: Gemma 3 27B⌄GoogleGood value$0.08$0.450%—
MODEL PROFILE

Google: Gemma 3 27B

API profile based on provider metadata: image input, ai agents & tools, structured output, long responses.

Image inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
google/gemma-3-27b-it
Published
Mar 12, 2025
Open model documentation ↗
Qwen: Qwen3 VL 32B Instruct⌄QwenGood value$0.104$0.4160%—
MODEL PROFILE

Qwen: Qwen3 VL 32B Instruct

API profile based on provider metadata: image input, coding, ai agents & tools, structured output, long responses.

Image inputCodingAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
32.8K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen3-vl-32b-instruct
Published
Oct 23, 2025
Open model documentation ↗
Google: Gemini 2.5 Flash Lite⌄GoogleGood value$0.1$0.40%—
MODEL PROFILE

Google: Gemini 2.5 Flash Lite

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-flash-lite
Published
Jul 22, 2025
Open model documentation ↗
OpenAI: GPT-4.1 Nano⌄OpenaiGood value$0.1$0.40%—
MODEL PROFILE

OpenAI: GPT-4.1 Nano

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-4.1-nano
Published
Apr 14, 2025
Open model documentation ↗
OpenAI: GPT-5 Nano⌄OpenaiGood value$0.05$0.40%—
MODEL PROFILE

OpenAI: GPT-5 Nano

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
10 supported
Model ID
openai/gpt-5-nano
Published
Aug 7, 2025
Open model documentation ↗
DeepSeek: DeepSeek V4 Flash Vision Exp (batch)⌄DeepseekBatch$0.11$0.330%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Flash Vision Exp (batch)

API profile based on provider metadata: image input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
18 supported
Model ID
deepseek/deepseek-v4-flash-vision-exp:batch
Published
Aug 21, 2026
Open model documentation ↗
DeepSeek: DeepSeek V4 Flash 0731 (batch)⌄DeepseekBatch$0.11$0.330%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Flash 0731 (batch)

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
943.7K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
deepseek/deepseek-v4-flash-0731:batch
Published
Jul 31, 2026
Open model documentation ↗
Qwen: Qwen3 235B A22B Instruct 2507⌄QwenGood value$0.0875$0.350%—
MODEL PROFILE

Qwen: Qwen3 235B A22B Instruct 2507

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-235b-a22b-2507
Published
Jul 21, 2025
Open model documentation ↗
Google: Gemma 4 31B⌄GoogleGood value$0.09$0.340%—
MODEL PROFILE

Google: Gemma 4 31B

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong context
Context window
262.1K tokens
Maximum output
16.4K tokens
Accepts
Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
google/gemma-4-31b-it
Published
Apr 2, 2026
Open model documentation ↗
Qwen: Qwen3.5-9B (batch)⌄QwenBatch$0.17$0.250%—
MODEL PROFILE

Qwen: Qwen3.5-9B (batch)

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3.5-9b:batch
Published
Mar 10, 2026
Open model documentation ↗
Meta: Llama 3.3 70B Instruct⌄Meta-llamaGood value$0.1$0.320%—
MODEL PROFILE

Meta: Llama 3.3 70B Instruct

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
meta-llama/llama-3.3-70b-instruct
Published
Dec 6, 2024
Open model documentation ↗
Mistral: Ministral 3 14B 2512⌄MistralaiGood value$0.2$0.20%—
MODEL PROFILE

Mistral: Ministral 3 14B 2512

API profile based on provider metadata: image input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/ministral-14b-2512
Published
Dec 2, 2025
Open model documentation ↗
Mistral: Voxtral Small 24B 2507⌄MistralaiGood value$0.1$0.30%—
MODEL PROFILE

Mistral: Voxtral Small 24B 2507

API profile based on provider metadata: audio, file input, ai agents & tools, structured output.

AudioFile inputAI agents & toolsStructured output
Context window
32.8K tokens
Maximum output
26.2K tokens
Accepts
Text, Audio, Files
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/voxtral-small-24b-2507
Published
Oct 30, 2025
Open model documentation ↗
Meta: Llama 4 Scout⌄Meta-llamaGood value$0.1$0.30%—
MODEL PROFILE

Meta: Llama 4 Scout

API profile based on provider metadata: image input, ai agents & tools, structured output, long context. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong context
Context window
1.3M tokens
Maximum output
16.4K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
meta-llama/llama-4-scout
Published
Apr 5, 2025
Open model documentation ↗
Google: Gemma 4 26B A4B ⌄GoogleGood value$0.09$0.30%—
MODEL PROFILE

Google: Gemma 4 26B A4B

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
google/gemma-4-26b-a4b-it
Published
Apr 3, 2026
Open model documentation ↗
Meta: Llama 3.2 3B Instruct⌄Meta-llamaGood value$0.05$0.330%—
MODEL PROFILE

Meta: Llama 3.2 3B Instruct

API profile based on provider metadata: structured output, long responses.

Structured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
meta-llama/llama-3.2-3b-instruct
Published
Sep 25, 2024
Open model documentation ↗
Mistral: Mistral Small 4 (batch)⌄MistralaiBatch$0.075$0.30%—
MODEL PROFILE

Mistral: Mistral Small 4 (batch)

API profile based on provider metadata: image input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
mistralai/mistral-small-2603:batch
Published
Mar 16, 2026
Open model documentation ↗
OpenAI: gpt-oss-safeguard-20b⌄OpenaiGood value$0.075$0.30%—
MODEL PROFILE

OpenAI: gpt-oss-safeguard-20b

API profile based on provider metadata: ai agents & tools, complex analysis, structured output, long responses.

AI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
65.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
openai/gpt-oss-safeguard-20b
Published
Oct 29, 2025
Open model documentation ↗
OpenAI: GPT-4o-mini (batch)⌄OpenaiBatch$0.075$0.30%—
MODEL PROFILE

OpenAI: GPT-4o-mini (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output.

Image inputFile inputAI agents & toolsStructured output
Context window
128K tokens
Maximum output
16.4K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
16 supported
Model ID
openai/gpt-4o-mini:batch
Published
Jul 18, 2024
Open model documentation ↗
Qwen: Qwen3 32B⌄QwenGood value$0.08$0.280%—
MODEL PROFILE

Qwen: Qwen3 32B

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output.

CodingAI agents & toolsComplex analysisStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
qwen/qwen3-32b
Published
Apr 29, 2025
Open model documentation ↗
Meta: Llama Guard 4 12B⌄Meta-llamaGood value$0.18$0.180%—
MODEL PROFILE

Meta: Llama Guard 4 12B

API profile based on provider metadata: image input, structured output.

Image inputStructured output
Context window
163.8K tokens
Maximum output
16.4K tokens
Accepts
Images, Text
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
meta-llama/llama-guard-4-12b
Published
Apr 30, 2025
Open model documentation ↗
Qwen: Qwen3 Coder 30B A3B Instruct⌄QwenGood value$0.07$0.280%—
MODEL PROFILE

Qwen: Qwen3 Coder 30B A3B Instruct

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
qwen/qwen3-coder-30b-a3b-instruct
Published
Jul 31, 2025
Open model documentation ↗
Qwen: Qwen3.5-Flash⌄QwenGood value$0.065$0.260%—
MODEL PROFILE

Qwen: Qwen3.5-Flash

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen3.5-flash-02-23
Published
Feb 25, 2026
Open model documentation ↗
Mistral: Ministral 3 8B 2512⌄MistralaiGood value$0.15$0.150%—
MODEL PROFILE

Mistral: Ministral 3 8B 2512

API profile based on provider metadata: image input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/ministral-8b-2512
Published
Dec 2, 2025
Open model documentation ↗
Qwen: Qwen2.5 7B Instruct⌄QwenGood value$0.1$0.20%—
MODEL PROFILE

Qwen: Qwen2.5 7B Instruct

API profile based on provider metadata: coding, ai agents & tools, structured output.

CodingAI agents & toolsStructured output
Context window
32.8K tokens
Maximum output
29.5K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
14 supported
Model ID
qwen/qwen-2.5-7b-instruct
Published
Oct 16, 2024
Open model documentation ↗
Mistral: Mistral Small 3.2 24B⌄MistralaiGood value$0.075$0.20%—
MODEL PROFILE

Mistral: Mistral Small 3.2 24B

API profile based on provider metadata: image input, ai agents & tools, structured output, long context. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong context
Context window
256K tokens
Maximum output
16.4K tokens
Accepts
Images, Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
mistralai/mistral-small-3.2-24b-instruct
Published
Jun 20, 2025
Open model documentation ↗
Qwen: Qwen3.5-9B⌄QwenGood value$0.1$0.150%—
MODEL PROFILE

Qwen: Qwen3.5-9B

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
235.9K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
19 supported
Model ID
qwen/qwen3.5-9b
Published
Mar 10, 2026
Open model documentation ↗
OpenAI: gpt-oss-20b (batch)⌄OpenaiBatch$0.05$0.20%—
MODEL PROFILE

OpenAI: gpt-oss-20b (batch)

API profile based on provider metadata: complex analysis, structured output, long responses.

Complex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
openai/gpt-oss-20b:batch
Published
Aug 5, 2025
Open model documentation ↗
Google: Gemini 2.5 Flash Lite (batch)⌄GoogleBatch$0.05$0.20%—
MODEL PROFILE

Google: Gemini 2.5 Flash Lite (batch)

API profile based on provider metadata: image input, audio, video input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioVideo inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Files, Audio, Video
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
google/gemini-2.5-flash-lite:batch
Published
Jul 22, 2025
Open model documentation ↗
OpenAI: GPT-4.1 Nano (batch)⌄OpenaiBatch$0.05$0.20%—
MODEL PROFILE

OpenAI: GPT-4.1 Nano (batch)

API profile based on provider metadata: image input, file input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputAI agents & toolsStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Files
Produces
Text
Safety moderation
Enabled
API features
8 supported
Model ID
openai/gpt-4.1-nano:batch
Published
Apr 14, 2025
Open model documentation ↗
Qwen: Qwen3 30B A3B Instruct 2507⌄QwenGood value$0.0482$0.19310%—
MODEL PROFILE

Qwen: Qwen3 30B A3B Instruct 2507

API profile based on provider metadata: coding, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
16 supported
Model ID
qwen/qwen3-30b-a3b-instruct-2507
Published
Jul 29, 2025
Open model documentation ↗
Meta: Llama 3.2 1B Instruct⌄Meta-llamaGood value$0.027$0.2010%—
MODEL PROFILE

Meta: Llama 3.2 1B Instruct

API profile based on provider metadata: long responses.

Long responses
Context window
60K tokens
Maximum output
54K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
meta-llama/llama-3.2-1b-instruct
Published
Sep 25, 2024
Open model documentation ↗
OpenAI: GPT-5 Nano (batch)⌄OpenaiBatch$0.025$0.20%—
MODEL PROFILE

OpenAI: GPT-5 Nano (batch)

API profile based on provider metadata: image input, file input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputFile inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
400K tokens
Maximum output
128K tokens
Accepts
Text, Images, Files
Produces
Text
Safety moderation
Enabled
API features
9 supported
Model ID
openai/gpt-5-nano:batch
Published
Aug 7, 2025
Open model documentation ↗
OpenAI: gpt-oss-120b⌄OpenaiGood value$0.037$0.170%—
MODEL PROFILE

OpenAI: gpt-oss-120b

API profile based on provider metadata: ai agents & tools, complex analysis, structured output, long responses.

AI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
21 supported
Model ID
openai/gpt-oss-120b
Published
Aug 5, 2025
Open model documentation ↗
Mistral: Ministral 3 3B 2512⌄MistralaiGood value$0.1$0.10%—
MODEL PROFILE

Mistral: Ministral 3 3B 2512

API profile based on provider metadata: image input, ai agents & tools, structured output, long responses.

Image inputAI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
104.9K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/ministral-3b-2512
Published
Dec 2, 2025
Open model documentation ↗
Google: Gemma 3 12B⌄GoogleGood value$0.05$0.150%—
MODEL PROFILE

Google: Gemma 3 12B

API profile based on provider metadata: image input, ai agents & tools, structured output.

Image inputAI agents & toolsStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
15 supported
Model ID
google/gemma-3-12b-it
Published
Mar 13, 2025
Open model documentation ↗
Qwen: Qwen3.7 Flash⌄QwenGood value$0.03$0.130%—
MODEL PROFILE

Qwen: Qwen3.7 Flash

API profile based on provider metadata: image input, video input, coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputCodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images, Video
Produces
Text
Safety moderation
Not declared
API features
12 supported
Model ID
qwen/qwen3.7-flash
Published
Jul 28, 2026
Open model documentation ↗
OpenAI: gpt-oss-20b⌄OpenaiGood value$0.03$0.130%—
MODEL PROFILE

OpenAI: gpt-oss-20b

API profile based on provider metadata: ai agents & tools, complex analysis, structured output, long responses.

AI agents & toolsComplex analysisStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
20 supported
Model ID
openai/gpt-oss-20b
Published
Aug 5, 2025
Open model documentation ↗
Mistral: Ministral 3 8B 2512 (batch)⌄MistralaiBatch$0.075$0.0750%—
MODEL PROFILE

Mistral: Ministral 3 8B 2512 (batch)

API profile based on provider metadata: image input, ai agents & tools, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAI agents & toolsStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
209.7K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
11 supported
Model ID
mistralai/ministral-8b-2512:batch
Published
Dec 2, 2025
Open model documentation ↗
Google: Gemma 3 4B⌄GoogleGood value$0.05$0.10%—
MODEL PROFILE

Google: Gemma 3 4B

API profile based on provider metadata: image input, structured output.

Image inputStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text, Images
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
google/gemma-3-4b-it
Published
Mar 14, 2025
Open model documentation ↗
DeepSeek: DeepSeek V4 Flash 0423⌄DeepseekGood value$0.0496$0.0991▼ 0.56%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Flash 0423

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
384K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
22 supported
Model ID
deepseek/deepseek-v4-flash
Published
Apr 24, 2026
Open model documentation ↗
Mistral: Mistral Small 3⌄MistralaiGood value$0.05$0.080%—
MODEL PROFILE

Mistral: Mistral Small 3

API profile based on provider metadata: structured output.

Structured output
Context window
32.8K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
13 supported
Model ID
mistralai/mistral-small-24b-instruct-2501
Published
Jan 30, 2025
Open model documentation ↗
Meta: Llama 3.1 8B Instruct⌄Meta-llamaGood value$0.05$0.080%—
MODEL PROFILE

Meta: Llama 3.1 8B Instruct

API profile based on provider metadata: ai agents & tools, structured output, long responses.

AI agents & toolsStructured outputLong responses
Context window
131.1K tokens
Maximum output
118K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
meta-llama/llama-3.1-8b-instruct
Published
Jul 23, 2024
Open model documentation ↗
DeepSeek: DeepSeek V4 Flash 0731⌄DeepseekGood value$0.04$0.080%—
MODEL PROFILE

DeepSeek: DeepSeek V4 Flash 0731

API profile based on provider metadata: coding, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

CodingAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
1.3M tokens
Maximum output
943.7K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
22 supported
Model ID
deepseek/deepseek-v4-flash-0731
Published
Jul 31, 2026
Open model documentation ↗
Mistral: Mistral Nemo⌄MistralaiGood value$0.019$0.030%—
MODEL PROFILE

Mistral: Mistral Nemo

API profile based on provider metadata: ai agents & tools, structured output.

AI agents & toolsStructured output
Context window
131.1K tokens
Maximum output
16.4K tokens
Accepts
Text
Produces
Text
Safety moderation
Not declared
API features
17 supported
Model ID
mistralai/mistral-nemo
Published
Jul 19, 2024
Open model documentation ↗
Google: Gemma 4 26B A4B (free)⌄GoogleFree$0$0——
MODEL PROFILE

Google: Gemma 4 26B A4B (free)

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
google/gemma-4-26b-a4b-it:free
Published
Apr 3, 2026
Open model documentation ↗
Google: Gemma 4 31B (free)⌄GoogleFree$0$0——
MODEL PROFILE

Google: Gemma 4 31B (free)

API profile based on provider metadata: image input, video input, ai agents & tools, complex analysis, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputVideo inputAI agents & toolsComplex analysisStructured outputLong contextLong responses
Context window
262.1K tokens
Maximum output
32.8K tokens
Accepts
Images, Text, Video
Produces
Text
Safety moderation
Not declared
API features
9 supported
Model ID
google/gemma-4-31b-it:free
Published
Apr 2, 2026
Open model documentation ↗
Google: Lyria 3 Pro Preview⌄GoogleFree$0$0——
MODEL PROFILE

Google: Lyria 3 Pro Preview

API profile based on provider metadata: image input, audio, coding, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioCodingStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images
Produces
Text, Audio
Safety moderation
Not declared
API features
5 supported
Model ID
google/lyria-3-pro-preview
Published
Mar 31, 2026
Open model documentation ↗
Google: Lyria 3 Clip Preview⌄GoogleFree$0$0——
MODEL PROFILE

Google: Lyria 3 Clip Preview

API profile based on provider metadata: image input, audio, coding, structured output, long context, long responses. Suitable for workloads with a large context window.

Image inputAudioCodingStructured outputLong contextLong responses
Context window
1M tokens
Maximum output
65.5K tokens
Accepts
Text, Images
Produces
Text, Audio
Safety moderation
Not declared
API features
5 supported
Model ID
google/lyria-3-clip-preview
Published
Mar 31, 2026
Open model documentation ↗

Estimates use currently published token rates. Caching, reasoning, tools, images and provider fees may change the final bill. Source: OpenRouter model API; official provider pages are used for editorial verification.

How to compare AI API token prices

AI API pricing usually has separate rates for input tokens sent to a model and output tokens generated in the response. Enter your typical prompt, answer length and number of requests in the calculator to compare GPT, Claude, Gemini, DeepSeek, Llama, Mistral and other models on the same workload.

Price per 1M tokens

The standard unit used by providers. The table keeps input and output rates separate so expensive generations do not disappear behind a low prompt price.

Estimated request cost

The calculator multiplies your input and output volume by the current rates. It is useful for prototypes, chatbots, agents, content pipelines and production forecasts.

Hourly price monitoring

The catalogue is checked every hour. The update time shown above tells you when the current snapshot was collected. Historical points accumulate from actual checks.

Frequently asked questions

What is an AI token?

A token is a text unit processed by a model. One token may be a word, part of a word, punctuation mark or other fragment, depending on the tokenizer.

Why are input and output prices different?

Generating new tokens generally requires more computation than reading a prompt, so providers often charge more for output.

Does the calculator show the final provider bill?

It provides an estimate based on published token rates. Caching, reasoning tokens, images, tools, minimum charges, routing and taxes may affect the final amount.

How often are AI model prices updated?

AI Feed checks the catalogue hourly. The timestamp at the top of the page shows the latest successful data snapshot.

Recent posts

  • AWS Details How to Deploy Interactive MCP Apps on AgentCore
  • xAI Makes Grok 4.6 Available in GitHub Copilot
  • Hugging Face and AWS Link Strands Robots to Streaming LeRobot Training
  • Anthropic Reports Claude Results in Protein Design and Chemistry
  • xAI Opens Grok Build to Every Plan on Web and Mobile

Recent comments

No comments to show.

Archives

  • September 2026
  • May 2026

Sections

  • AI Comparisons
  • AI Features
  • AI Guides
  • AI News
  • Uncategorized

    © 2026 AI Feed. All rights reserved.
    RUEN
    AboutEditorial PolicySources & methodologyCorrectionsContactPrivacyAnalytics settings
    AI Feed analytics

    Helps us understand which pages are useful. Advertising tracking is disabled.