The Orchestrator › Models › Mistral AI
Mistral AI: Mistral: Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/mistral-small-2603 |
| Context window | 262K tokens (262,144) |
| Modalities | text + image → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-03-16 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/mistral-small-2603 | $0.15 | $0.6 | 262K |
| standard | TrustedRouter | mistralai/mistral-small-2603 | $0.158 | $0.633 | 262K |
| alias | Vercel AI Gateway | mistralai/mistral-small | $0.15 | $0.6 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.158 | $0.633 | 262K |
| 2026-11-14 | $0.15 | $0.6 | 262K |
Capabilities
Vision (image input)Agentic tool useStructured outputs256K+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p