Mistral: Mistral Small 4 vs openai/gpt-oss-120b-Turbo
They cost about the same for input tokens: Mistral: Mistral Small 4 $0.15 per M, openai/gpt-oss-120b-Turbo $0.15 per M. They cost about the same for output tokens: Mistral: Mistral Small 4 $0.60 per M, openai/gpt-oss-120b-Turbo $0.60 per M. Mistral: Mistral Small 4 reads more: Mistral: Mistral Small 4 takes up to 262,144 tokens of context and openai/gpt-oss-120b-Turbo up to 131,072. Mistral: Mistral Small 4 accepts image, text; openai/gpt-oss-120b-Turbo accepts text.
| Mistral: Mistral Small 4 | openai/gpt-oss-120b-Turbo | |
|---|---|---|
| Model id | mistralai/mistral-small-2603 | openai/gpt-oss-120b-Turbo |
| Input | $0.15 per M | $0.15 per M |
| Output | $0.60 per M | $0.60 per M |
| Context length | 262,144 tokens | 131,072 tokens |
| Accepts | image, text | text |
| Produces | text | text |
| Served by | mistral | deepinfra |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.