Mistral Large 3 Chat: pricing, context window and benchmarks
Mistral Large 3 Chat is a multimodal model from Mistral AI. It offers a 1,000,000-token context window, costs $4.90 per million input tokens and $20.04 per million output tokens, and averages 79.1 across the index's benchmark suite.
Pricing
Mistral Large 3 Chat costs $4.90 per million input tokens and $20.04 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.69 per million tokens. Cached input is listed at $0.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.90 | per 1M tokens |
| Output | $20.04 | per 1M tokens |
| Cached input | $0.41 | per 1M tokens |
| Blended 3:1 | $8.69 | estimate per 1M tokens |
| 1M in + 1M out | $24.94 | 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 | 83.3 | 101 | 83th | |
| GPQA Diamond | 75.9 | 123 | 80th | |
| SWE-bench Verified | 67.1 | 167 | 72th | |
| HumanEval | 85.0 | 119 | 80th | |
| MATH-500 | 81.6 | 175 | 71th | |
| AIME 2025 | 74.1 | 178 | 70th | |
| LiveCodeBench | 73.0 | 128 | 79th | |
| IFEval | 86.6 | 143 | 76th | |
| TruthfulQA | 80.2 | 173 | 71th | |
| HellaSwag | 87.1 | 174 | 71th | |
| MMMU | 76.6 | 121 | 80th | |
| Arena Elo | 1414.2 | 172 | 71th |
What Mistral Large 3 Chat is good for
Mistral Large 3 Chat is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.90 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 1,000,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
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 |
|---|---|---|---|---|
| Llama 4 Maverick Base | Meta AI | 128000 | $4.68 | 79.1 |
| Llama 4 Scout Instruct | Meta AI | 32768 | $4.59 | 79.1 |
| Mistral Large 3 Chat | Mistral AI | 1000000 | $4.90 | 79.1 |
| Qwen3 Chat | Alibaba Cloud | 128000 | $4.75 | 79.1 |
| Sonar Pro | Perplexity | 128000 | $13.01 | 79.1 |
| Claude Opus 4.5 Mini | Anthropic | 65536 | $12.72 | 79.0 |
FAQ
How much does Mistral Large 3 Chat cost?
Mistral Large 3 Chat is listed at $4.90 per million input tokens and $20.04 per million output tokens. Cached input is $0.41 per million tokens. A blended 3:1 input-to-output mix is about $8.69 per million tokens.
What is the context window of Mistral Large 3 Chat?
Mistral Large 3 Chat has a context window of 1,000,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is Mistral Large 3 Chat open weights?
Yes. Mistral Large 3 Chat is listed as an open-weight model under a open weights licence.
How does Mistral Large 3 Chat score on benchmarks?
Mistral Large 3 Chat averages 79.1 across the scored benchmarks in this index, ranking #146 of 600 models. Its strongest relative result is Arena Elo at 1414.2.
What is Mistral Large 3 Chat best for?
Mistral Large 3 Chat is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.90 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.