Mistral Small 3 8B: pricing, context window and benchmarks
Mistral Small 3 8B is a small open-weight model from Mistral AI. It offers a 8,192-token context window, costs $0.99 per million input tokens and $5.38 per million output tokens, and averages 57.2 across the index's benchmark suite.
Pricing
Mistral Small 3 8B costs $0.99 per million input tokens and $5.38 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.09 per million tokens. Cached input is listed at $0.12 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.99 | per 1M tokens |
| Output | $5.38 | per 1M tokens |
| Cached input | $0.12 | per 1M tokens |
| Blended 3:1 | $2.09 | estimate per 1M tokens |
| 1M in + 1M out | $6.37 | 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 | 62.6 | 494 | 18th | |
| GPQA Diamond | 51.8 | 501 | 17th | |
| SWE-bench Verified | 40.7 | 514 | 14th | |
| HumanEval | 61.3 | 478 | 20th | |
| MATH-500 | 55.5 | 516 | 14th | |
| AIME 2025 | 47.5 | 473 | 21th | |
| LiveCodeBench | 45.8 | 489 | 19th | |
| IFEval | 68.9 | 477 | 21th | |
| TruthfulQA | 62.9 | 494 | 18th | |
| HellaSwag | 73.5 | 468 | 22th | |
| MMMU | 58.3 | 453 | 25th | |
| Arena Elo | 1253.4 | 485 | 19th |
What Mistral Small 3 8B is good for
Mistral Small 3 8B 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 $0.99 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.99 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 8,192 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 |
|---|---|---|---|---|
| DeepSeek-Coder 7B | DeepSeek | 32768 | $1.14 | 57.3 |
| Llama 3 Anyscale 8B | Anyscale | 32768 | $0.97 | 57.3 |
| Llama 3 Lambda 8B | Lambda | 4096 | $1.03 | 57.2 |
| Mistral Small 3 8B | Mistral AI | 8192 | $0.99 | 57.2 |
| Auto Nano | OpenRouter | 4096 | $2.83 | 57.1 |
| Seed-OSS 8B | ByteDance | 8192 | $1.05 | 57.1 |
FAQ
How much does Mistral Small 3 8B cost?
Mistral Small 3 8B is listed at $0.99 per million input tokens and $5.38 per million output tokens. Cached input is $0.12 per million tokens. A blended 3:1 input-to-output mix is about $2.09 per million tokens.
What is the context window of Mistral Small 3 8B?
Mistral Small 3 8B has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Mistral Small 3 8B open weights?
Yes. Mistral Small 3 8B is listed as an open-weight model under a open weights licence.
How does Mistral Small 3 8B score on benchmarks?
Mistral Small 3 8B averages 57.2 across the scored benchmarks in this index, ranking #484 of 600 models. Its strongest relative result is Arena Elo at 1253.4.
What is Mistral Small 3 8B best for?
Mistral Small 3 8B 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 $0.99 per million input tokens it can handle a large share of production traffic.