MMistral · Released Mar 16, 2026
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...
- Released
- Mar 16 2026
- Context window
- 262K 210K out
- Input / 1M tokens
- $0.15
- Output / 1M tokens
- $0.60
Where to run it
19 providers compared
Cheapest: Mistral, Kilo Gateway, LLM Gateway +6 more at $0.15 / $0.60 per 1M input / output tokens — 75% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Mistralzdr | $0.15 | $0.60 | $0.015 | 262K | 210K | 99.9%24h | Cheapest |
| Mistral | $0.15 | $0.60 | $0.015 | 262K | 210K | 99.9%24h | Cheapest |
| Kilo Gateway | $0.15 | $0.60 | $0.015 | 262K | 210K | — | Cheapest |
| LLM Gateway | $0.15 | $0.60 | — | 262K | 256K | — | Cheapest |
| Pioneer | $0.15 | $0.60 | $0.015 | 32K | 32K | — | Cheapest |
| SAP AI Core | $0.15 | $0.60 | — | 128K | 128K | — | Cheapest |
| Tempr Gateway | $0.15 | $0.60 | $0.015 | 256K | 256K | — | Cheapest |
| DevPass (LLM Gateway) | $0.15 | $0.60 | — | 262K | 256K | — | Cheapest |
| EmpirioLabs AI | $0.15 | $0.60 | $0.15 | 256K | 66K | — | Cheapest |
| Eden AI | $0.15 | $0.60 | $0.015 | 262K | 256K | — | Cheapest |
| Cortecs | $0.16 | $0.63 | $0.016 | 262K | 256K | — | +4% |
| LowRouter | $0.16 | $0.63 | $0.016 | 256K | 256K | — | +5% |
| Mistraleu | $0.17 | $0.66 | $0.016 | 262K | 210K | 100%24h | +10% |
| Mistralus | $0.17 | $0.66 | $0.016 | 262K | 210K | 100%24h | +10% |
| Requesty | $0.17 | $0.66 | $0.17 | 256K | 256K | — | +10% |
| Prime Inference | $0.17 | $0.66 | — | 262K | 210K | — | +10% |
| AKI.IO | $0.22 | $0.67 | — | 262K | 82K | — | +28% |
| Infomaniak | $0.25 | $0.93 | — | 256K | 256K | — | +60% |
| AI/ML API | $0.26 | $1.03 | $0.021 | 262K | 256K | — | +72% |
| NanoGPT | $0.40 | $1.40 | $0.20 | 262K | 16K | — | +148% |
| Regolo AI | $0.56 | $2.35 | — | 256K | 16K | — | +285% |
| Opper | $0.58 | $2.44 | — | 256K | 8K | — | +298% |
Value
Price vs. performance
Mistral Small 4 Other Mistral Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
5 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 27.8% | #97of 102 | Claude Opus 5.566.9% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 47.5% | #107of 122 | Gemini 4 Argon96.4% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 0.0% | #92of 111 | GPT-5.6 Sol32.3% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 20.6% | #95of 123 | Claude Sonnet 5.568.3% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 5.8% | #112of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
mistralai/mistral-small-2603- Developer
- Mistral
- Release date
- Mar 16, 2026 ·
- Context window
- 262,144 tokens
- Max output
- 209,715 tokens
- API price
- $0.15 / $0.60 per 1M input / output tokens
- Providers
- 19
- Input types
- text, image
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.