mistralai
Mistral: Mistral Small 4
mistralai/mistral-small-2603
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Mistral Small 4 (mistralai/mistral-small-2603) is a 119B-parameter mixture-of-experts model from Mistral that, per its model card, unifies instruction-following, reasoning, and coding capabilities in one system. It takes text and image input, returns text, and offers a 256k context window plus per-request reasoning-effort control. The card reports efficiency gains over Mistral Small 3 and competitive benchmark results, while OpenRouter's catalog lists its own aggregate scores. Vendor-reported figures should be validated on real workloads.[1][2]
Strengths
- Single system covering instruct, reasoning, and coding-oriented (Devstral-derived) roles, with reasoning effort switchable per request, per the model card.[2]
- Text and image input with text output and a 256k context window, plus native function calling and structured JSON output.[1][2]
- Vendor reports notable latency and throughput improvements over Mistral Small 3 and shorter outputs at comparable benchmark performance; open weights under the Apache 2.0 license.[2]
Limitations
- Evidence rests on a vendor model card and an aggregator catalog; benchmark figures are vendor-reported and not independently reproduced.[1][2]
- Knowledge cutoff, hardware requirements, and safety evaluations are not stated in the supplied sources; validate on your own workloads before production use.[1][2]
Where to use it
- General chat assistants and agents, including tool-calling workflows, per the vendor's suggested uses.[2]
- Document parsing, image understanding, and data extraction using its multimodal input.[2]
- Coding assistants and software engineering automation; the vendor also suggests fine-tuning for specialized tasks.[2]
Sources
- [1] OpenRouter catalog · Mistral: Mistral Small 4Sources checked: Nov 13, 2026
- [2] Model documentation · Mistral: Mistral Small 4Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Model ID
- mistralai/mistral-small-2603
- Creator
- mistralai
- Added to OpenRouter
- 16.03.2026
- Context length
- 262,144
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.150 / out $0.600
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 4.3 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 26.6 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.8 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 262,144 | $0.150 | $0.600 | — | — | 100% |
| Mistral | 262,144 | $0.165 | $0.660 | — | — | 100% |
| Mistral | 262,144 | $0.165 | $0.660 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.