OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 5 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Mistral (7B) Instruct v0.1 This page | ||||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Yes, Mistral (7B) Instruct v0.1 can stream responses as they are generated.
Yes, Mistral (7B) Instruct v0.1 supports both function calling and structured outputs.
Mistral (7B) Instruct v0.1 was built by Mistral AI.
It is accessed via the v1/chat/completions endpoint.
