Mistral API pricing
Mistral API prices per million tokens, context windows, open-weights status and independent benchmark scores.
Prices updated . Benchmarks updated .
Prices are the current OpenRouter rate, refreshed about hourly. This page does not chart older prices.
| Model | You send / 1M | It replies / 1M | Context | ECI | Launched |
|---|---|---|---|---|---|
| Mistral Large 4Open weights, restricted | $0.700 | $2.10 | 1M | 150.6 | 2026-10-06 |
| Mistral Medium 3.5Open weights, restricted | $1.50 | $7.50 | 262K | 141.5 | 2026-04-30 |
| Mistral Medium 3Closed | $0.400 | $2.00 | 131K | 134.0 | 2025-05-07 |
| Mistral LargeOpen weights | $2.00 | $6.00 | 128K | 122.0 | 2024-11-18 |
| Mistral NemoOpen weights | $0.029 | $0.030 | 128K | 118.6 | 2024-07-18 |
| Mistral Small 4Open weights | $0.150 | $0.600 | 262K | n/a | 2026-03-16 |
| Devstral 2 2512Open weights | $0.400 | $2.00 | 262K | n/a | 2025-12-09 |
| Ministral 3 14B 2512Open weights | $0.200 | $0.200 | 262K | n/a | 2025-12-02 |
| Ministral 3 8B 2512Open weights | $0.150 | $0.150 | 262K | n/a | 2025-12-02 |
| Ministral 3 3B 2512Open weights | $0.100 | $0.100 | 131K | n/a | 2025-12-02 |
| Mistral Large 3 2512Open weights | $0.500 | $1.50 | 262K | n/a | 2025-12-02 |
| Mistral Medium 3.1Closed | $0.400 | $2.00 | 131K | n/a | 2025-08-12 |
| Codestral 2508Closed | $0.300 | $0.900 | 256K | n/a | 2025-07-30 |
| Voxtral Small 24B 2507Open weights | $0.100 | $0.300 | 33K | n/a | 2025-07-15 |
| Mistral Small 3.2 24BOpen weights | $0.075 | $0.200 | 256K | n/a | 2025-06-20 |
| Mistral Small 3.1 24BOpen weights | $0.351 | $0.555 | 128K | n/a | 2025-03-17 |
| SabaClosed | $0.200 | $0.600 | 33K | n/a | 2025-02-17 |
| Mistral Small 3Open weights | $0.050 | $0.080 | 33K | n/a | 2025-01-30 |
| Mistral Large 2407Open weights | $2.00 | $6.00 | 131K | n/a | 2024-07-24 |
| Mixtral 8x22B InstructOpen weights | $2.00 | $6.00 | 66K | n/a | 2024-04-17 |
Which Mistral model ranks highest?
Mistral Large 4 has the highest Epoch Capabilities Index among Mistral models on this page, at 150.6. Mistral Medium 3.5 is next at 141.5. Mistral Large 4 costs $2.10 per million output tokens and reads 1M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Mistral model is cheapest?
Mistral Nemo has the lowest published output price among Mistral models here, at $0.030 per million tokens. Input tokens cost $0.029 per million and the context window is 128K. Mistral Small 3 is next at $0.080 per million output tokens. Its Epoch Capabilities Index is 118.6. Prices are the current public rate and can change.
Which Mistral open-weight models lead?
Mistral Large leads Mistral open-weight models that have a published Epoch Capabilities Index, at 122.0. It is from Mistral, costs $6.00 per million output tokens, and reads 128K. Mistral Nemo from Mistral follows at 118.6. Open weights means the lab published the weights. The license on the model page says what you can do with them.
FAQ
Which Mistral model ranks highest?
Mistral Large 4 has the highest Epoch Capabilities Index among Mistral models on this page, at 150.6. Mistral Medium 3.5 is next at 141.5. Mistral Large 4 costs $2.10 per million output tokens and reads 1M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Mistral model is cheapest?
Mistral Nemo has the lowest published output price among Mistral models here, at $0.030 per million tokens. Input tokens cost $0.029 per million and the context window is 128K. Mistral Small 3 is next at $0.080 per million output tokens. Its Epoch Capabilities Index is 118.6. Prices are the current public rate and can change.
How many Mistral models are listed?
This page lists 20 Mistral models with a public price or an independent score. Open the comparison table to filter the full catalogue.
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.