Mistral Small 3 Chat: pricing, context window and benchmarks
Mistral Small 3 Chat is a multimodal model from Mistral AI. It offers a 200,000-token context window, costs $3.54 per million input tokens and $16.77 per million output tokens, and averages 73.7 across the index's benchmark suite.
Pricing
Mistral Small 3 Chat costs $3.54 per million input tokens and $16.77 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.85 per million tokens. Cached input is listed at $0.40 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.54 | per 1M tokens |
| Output | $16.77 | per 1M tokens |
| Cached input | $0.40 | per 1M tokens |
| Blended 3:1 | $6.85 | estimate per 1M tokens |
| 1M in + 1M out | $20.31 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 76.7 | 286 | 52th | |
| GPQA Diamond | 68.2 | 310 | 48th | |
| SWE-bench Verified | 61.6 | 291 | 52th | |
| HumanEval | 80.1 | 231 | 62th | |
| MATH-500 | 75.2 | 322 | 46th | |
| AIME 2025 | 66.9 | 315 | 48th | |
| LiveCodeBench | 67.6 | 235 | 61th | |
| IFEval | 82.9 | 247 | 59th | |
| TruthfulQA | 78.8 | 226 | 62th | |
| HellaSwag | 82.6 | 333 | 45th | |
| MMMU | 70.4 | 285 | 53th | |
| Arena Elo | 1387.4 | 257 | 57th |
What Mistral Small 3 Chat is good for
Mistral Small 3 Chat is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.54 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Input price of $3.54 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Grok 3 Mini | xAI | 200000 | $9.67 | 73.9 |
| Mistral Small 3 Chat | Mistral AI | 200000 | $3.54 | 73.7 |
| Mixtral | Mistral AI | 65536 | $3.48 | 73.7 |
| Gemma 3 | Google DeepMind | 65536 | $3.68 | 73.6 |
| GPT-5.2 Nano | OpenAI | 128000 | $9.73 | 73.5 |
| Yi-Large | 01.AI | 32768 | $3.40 | 73.5 |
FAQ
How much does Mistral Small 3 Chat cost?
Mistral Small 3 Chat is listed at $3.54 per million input tokens and $16.77 per million output tokens. Cached input is $0.40 per million tokens. A blended 3:1 input-to-output mix is about $6.85 per million tokens.
What is the context window of Mistral Small 3 Chat?
Mistral Small 3 Chat has a context window of 200,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is Mistral Small 3 Chat open weights?
Yes. Mistral Small 3 Chat is listed as an open-weight model under a open weights licence.
How does Mistral Small 3 Chat score on benchmarks?
Mistral Small 3 Chat averages 73.7 across the scored benchmarks in this index, ranking #282 of 600 models. Its strongest relative result is Arena Elo at 1387.4.
What is Mistral Small 3 Chat best for?
Mistral Small 3 Chat is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.54 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.