Gemini API vs OpenAI pricing
Compare Gemini and OpenAI prices for chatbots, content and long-context workloads.
Compare one workload
Rates only become comparable when input, output and request count are identical. The calculation below uses the same workload for every model.
- Input per request
- 2,000
- Output per request
- 1,000
- Requests
- 1,000
Current model costs
| Model | Input / 1M | Output / 1M | Workload estimate |
|---|---|---|---|
| OpenAI: GPT-6.1 Sol ProOpenai | $2 | $10 | $14 |
| OpenAI: GPT-6.1 SolOpenai | $2 | $10 | $14 |
| OpenAI: GPT-6 Luna ProOpenai | $0.1 | $0.5 | $0.7 |
| OpenAI: GPT-6 LunaOpenai | $0.1 | $0.5 | $0.7 |
| OpenAI: GPT-6 Sol ProOpenai | $2 | $10 | $14 |
| OpenAI: GPT-6 SolOpenai | $2 | $10 | $14 |
| OpenAI: GPT-6 AstraOpenai | $10 | $50 | $70 |
| OpenAI: GPT-6 Astra ProOpenai | $10 | $50 | $70 |
| Google: Gemini 3.8 FlashGoogle | $0.75 | $3.75 | $5.25 |
| Google: Gemini 3.7 FlashGoogle | $0.75 | $3.75 | $5.25 |
| Google: Gemini 3.6 FlashGoogle | $0.75 | $3.75 | $5.25 |
| Google: Gemini 3.5 Flash LiteGoogle | $0.3 | $2.5 | $3.1 |
Estimate uses published token rates. Caching, reasoning tokens, tools, images, routing and taxes can change the final bill.
Which is cheaper: Gemini API or OpenAI?
Start with the work unit you can measure: one conversation, document, article or agent run. Record both prompt and response length, then multiply by real monthly volume. Output often costs more than input, so a concise answer can matter more than a short prompt.
Price is only one constraint. Check context length, modalities, tool support, latency and output quality before choosing a production model. Test a small representative sample instead of relying on a single benchmark.