Mistral Large 3 8B: pricing, context window and benchmarks
Mistral Large 3 8B is a small open-weight model from Mistral AI. It offers a 16,384-token context window, costs $1.62 per million input tokens and $6.82 per million output tokens, and averages 61.6 across the index's benchmark suite.
Pricing
Mistral Large 3 8B costs $1.62 per million input tokens and $6.82 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.92 per million tokens. Cached input is listed at $0.14 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.62 | per 1M tokens |
| Output | $6.82 | per 1M tokens |
| Cached input | $0.14 | per 1M tokens |
| Blended 3:1 | $2.92 | estimate per 1M tokens |
| 1M in + 1M out | $8.44 | 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 | 64.7 | 459 | 24th | |
| GPQA Diamond | 55.7 | 453 | 25th | |
| SWE-bench Verified | 48.9 | 430 | 28th | |
| HumanEval | 66.5 | 425 | 29th | |
| MATH-500 | 61.0 | 452 | 25th | |
| AIME 2025 | 53.3 | 430 | 28th | |
| LiveCodeBench | 52.1 | 429 | 29th | |
| IFEval | 73.7 | 408 | 32th | |
| TruthfulQA | 65.7 | 449 | 25th | |
| HellaSwag | 76.3 | 422 | 30th | |
| MMMU | 59.7 | 431 | 28th | |
| Arena Elo | 1301.3 | 417 | 31th |
What Mistral Large 3 8B is good for
Mistral Large 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 $1.62 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.62 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 16,384 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 |
|---|---|---|---|---|
| GLM-4.6 7B | Zhipu AI | 16384 | $1.52 | 61.8 |
| GPT-NeoX | EleutherAI | 16384 | $1.57 | 61.7 |
| MiniMax-M2 8B | MiniMax | 32768 | $1.65 | 61.7 |
| Auto Mini | OpenRouter | 4096 | $4.24 | 61.6 |
| Mistral Large 3 8B | Mistral AI | 16384 | $1.62 | 61.6 |
| Firesearch Mini | Fireworks AI | 32768 | $3.94 | 61.5 |
FAQ
How much does Mistral Large 3 8B cost?
Mistral Large 3 8B is listed at $1.62 per million input tokens and $6.82 per million output tokens. Cached input is $0.14 per million tokens. A blended 3:1 input-to-output mix is about $2.92 per million tokens.
What is the context window of Mistral Large 3 8B?
Mistral Large 3 8B has a context window of 16,384 tokens and can emit up to 8,192 output tokens per request in this index.
Is Mistral Large 3 8B open weights?
Yes. Mistral Large 3 8B is listed as an open-weight model under a open weights licence.
How does Mistral Large 3 8B score on benchmarks?
Mistral Large 3 8B averages 61.6 across the scored benchmarks in this index, ranking #437 of 600 models. Its strongest relative result is Arena Elo at 1301.3.
What is Mistral Large 3 8B best for?
Mistral Large 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 $1.62 per million input tokens it can handle a large share of production traffic.