Mistral Small 3 7B: pricing, context window and benchmarks
Mistral Small 3 7B is a small open-weight model from Mistral AI. It offers a 4,096-token context window, costs $0.89 per million input tokens and $4.71 per million output tokens, and averages 55.2 across the index's benchmark suite.
Pricing
Mistral Small 3 7B costs $0.89 per million input tokens and $4.71 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.84 per million tokens. Cached input is listed at $0.11 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.89 | per 1M tokens |
| Output | $4.71 | per 1M tokens |
| Cached input | $0.11 | per 1M tokens |
| Blended 3:1 | $1.84 | estimate per 1M tokens |
| 1M in + 1M out | $5.60 | 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 | 58.8 | 540 | 10th | |
| GPQA Diamond | 48.9 | 535 | 11th | |
| SWE-bench Verified | 43.1 | 490 | 18th | |
| HumanEval | 60.5 | 496 | 17th | |
| MATH-500 | 55.6 | 513 | 15th | |
| AIME 2025 | 47.4 | 474 | 21th | |
| LiveCodeBench | 44.1 | 507 | 16th | |
| IFEval | 65.8 | 522 | 13th | |
| TruthfulQA | 60.6 | 523 | 13th | |
| HellaSwag | 72.1 | 494 | 18th | |
| MMMU | 50.8 | 546 | 9th | |
| Arena Elo | 1246.3 | 496 | 17th |
What Mistral Small 3 7B is good for
Mistral Small 3 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.89 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.89 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 4,096 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3 Lambda 7B | Lambda | 8192 | $0.84 | 55.4 |
| Mistral Large 3 1.5B | Mistral AI | 32768 | $0.82 | 55.4 |
| Llama 3 Baseten 7B | Baseten | 32768 | $0.87 | 55.3 |
| Llama 3 Modal 7B | Modal | 4096 | $0.88 | 55.2 |
| Llama 4 Maverick 1.5B | Meta AI | 8192 | $0.93 | 55.2 |
| Mistral Small 3 7B | Mistral AI | 4096 | $0.89 | 55.2 |
FAQ
How much does Mistral Small 3 7B cost?
Mistral Small 3 7B is listed at $0.89 per million input tokens and $4.71 per million output tokens. Cached input is $0.11 per million tokens. A blended 3:1 input-to-output mix is about $1.84 per million tokens.
What is the context window of Mistral Small 3 7B?
Mistral Small 3 7B has a context window of 4,096 tokens and can emit up to 4,096 output tokens per request in this index.
Is Mistral Small 3 7B open weights?
Yes. Mistral Small 3 7B is listed as an open-weight model under a open weights licence.
How does Mistral Small 3 7B score on benchmarks?
Mistral Small 3 7B averages 55.2 across the scored benchmarks in this index, ranking #522 of 600 models. Its strongest relative result is Arena Elo at 1246.3.
What is Mistral Small 3 7B best for?
Mistral Small 3 7B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.89 per million input tokens it can handle a large share of production traffic.