Mistral Small 3 Instruct: pricing, context window and benchmarks
Mistral Small 3 Instruct is a multimodal model from Mistral AI. It offers a 32,768-token context window, costs $3.97 per million input tokens and $20.95 per million output tokens, and averages 75.1 across the index's benchmark suite.
Pricing
Mistral Small 3 Instruct costs $3.97 per million input tokens and $20.95 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.21 per million tokens. Cached input is listed at $0.39 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.97 | per 1M tokens |
| Output | $20.95 | per 1M tokens |
| Cached input | $0.39 | per 1M tokens |
| Blended 3:1 | $8.21 | estimate per 1M tokens |
| 1M in + 1M out | $24.92 | 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 | 78.3 | 233 | 61th | |
| GPQA Diamond | 70.0 | 264 | 56th | |
| SWE-bench Verified | 62.2 | 277 | 54th | |
| HumanEval | 79.7 | 243 | 60th | |
| MATH-500 | 80.5 | 200 | 67th | |
| AIME 2025 | 68.2 | 294 | 51th | |
| LiveCodeBench | 68.2 | 224 | 63th | |
| IFEval | 85.3 | 178 | 70th | |
| TruthfulQA | 76.1 | 303 | 50th | |
| HellaSwag | 85.0 | 246 | 59th | |
| MMMU | 72.9 | 224 | 63th | |
| Arena Elo | 1385.0 | 265 | 56th |
What Mistral Small 3 Instruct is good for
Mistral Small 3 Instruct 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 $3.97 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.97 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 |
|---|---|---|---|---|
| Codestral Instruct | Mistral AI | 65536 | $4.01 | 75.1 |
| Llama 3 Hyperbolic Chat | Hyperbolic | 200000 | $3.64 | 75.1 |
| Llama 3 Replicate Instruct | Replicate | 128000 | $3.71 | 75.1 |
| Mistral Small 3 Instruct | Mistral AI | 32768 | $3.97 | 75.1 |
| Reka Flash Turbo | Reka AI | 128000 | $10.19 | 75.1 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
FAQ
How much does Mistral Small 3 Instruct cost?
Mistral Small 3 Instruct is listed at $3.97 per million input tokens and $20.95 per million output tokens. Cached input is $0.39 per million tokens. A blended 3:1 input-to-output mix is about $8.21 per million tokens.
What is the context window of Mistral Small 3 Instruct?
Mistral Small 3 Instruct has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is Mistral Small 3 Instruct open weights?
Yes. Mistral Small 3 Instruct is listed as an open-weight model under a open weights licence.
How does Mistral Small 3 Instruct score on benchmarks?
Mistral Small 3 Instruct averages 75.1 across the scored benchmarks in this index, ranking #251 of 600 models. Its strongest relative result is Arena Elo at 1385.0.
What is Mistral Small 3 Instruct best for?
Mistral Small 3 Instruct 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 $3.97 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.