Mistral · October 2026
Mistral API pricing, every model
20 Mistral models, from $0.029 to $2 per million input tokens. European models from small to large, plus Codestral for code.
Prices from OpenRouter’s models API, updated October 29, 2026
Mistral Nemo
$0.029 in · $0.03 outAbout $1.67 a month for a 1,000-chats-a-day support bot.
Mistral Large 4
$1.36 in · $4.18 outReleased 2026-10-06, 1.05M tokens of context.
Devstral 2 2512
−90%Cached input costs $0.04 instead of $0.40 per 1M tokens.
All Mistral models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Batch in / out | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|---|
| Mistral Large 4 | 2026-10-06 | $1.36 | $4.18 | $0.14 | – | 1.05M | $111 |
| Mistral Medium 3.5 | 2026-04-30 | $1.50 | $7.50 | – | $0.75 / $3.75 | 262K | $158 |
| Mistral Small 4 | 2026-03-16 | $0.15 | $0.60 | $0.015 | – | 262K | $13.95 |
| Devstral 2 2512 | 2025-12-09 | $0.40 | $2 | $0.04 | – | 262K | $42.00 |
| Ministral 3 14B 2512 | 2025-12-02 | $0.20 | $0.20 | $0.02 | – | 262K | $11.40 |
| Ministral 3 3B 2512 | 2025-12-02 | $0.10 | $0.10 | $0.01 | – | 131K | $5.70 |
| Ministral 3 8B 2512 | 2025-12-02 | $0.15 | $0.15 | $0.015 | – | 262K | $8.55 |
| Mistral Large 3 2512 | 2025-12-01 | $0.50 | $1.50 | $0.05 | – | 262K | $40.50 |
| Voxtral Small 24B 2507 | 2025-10-30 | $0.10 | $0.30 | $0.01 | – | 33K | $8.10 |
| Mistral Medium 3.1 | 2025-08-13 | $0.40 | $2 | $0.04 | – | 131K | $42.00 |
| Codestral 2508 | 2025-08-01 | $0.30 | $0.90 | $0.03 | – | 256K | $24.30 |
| Mistral Small 3.2 24B | 2025-06-20 | $0.075 | $0.20 | – | – | 256K | $5.77 |
| Mistral Medium 3 | 2025-05-07 | $0.40 | $2 | $0.04 | – | 131K | $42.00 |
| Mistral Small 3.1 24B | 2025-03-17 | $0.351 | $0.555 | – | – | 128K | $22.46 |
| Saba | 2025-02-17 | $0.20 | $0.60 | $0.02 | – | 33K | $16.20 |
| Mistral Small 3 | 2025-01-30 | $0.05 | $0.08 | – | – | 33K | $3.21 |
| Mistral Large 2407 | 2024-11-19 | $2 | $6 | $0.20 | – | 131K | $162 |
| Mistral Nemo | 2024-07-19 | $0.029 | $0.03 | – | – | 131K | $1.67 |
| Mixtral 8x22B Instruct | 2024-04-17 | $2 | $6 | $0.20 | – | 66K | $162 |
| Mistral Large | 2024-02-26 | $2 | $6 | $0.20 | – | 128K | $162 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| Mistral Nemo | $1.67 | $28.80 | $21.60 |
| Mistral Small 3 | $3.21 | $52.20 | $37.92 |
| Ministral 3 3B 2512 | $5.70 | $99.00 | $22.56 |
| Mistral Small 3.2 24B | $5.77 | $85.50 | $58.80 |
| Ministral 3 8B 2512 | $8.55 | $149 | $33.84 |
| Voxtral Small 24B 2507 | $8.10 | $117 | $27.36 |
| Ministral 3 14B 2512 | $11.40 | $198 | $45.12 |
| Mistral Small 4 | $13.95 | $189 | $44.64 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
Mistral pricing questions
How much does the Mistral API cost?
Mistral’s models range from $0.029 per 1M input tokens and $0.03 per 1M output tokens (Mistral Nemo) to $2 and $6 (Mistral Large). The newest, Mistral Large 4, costs $1.36 in and $4.18 out.
Which Mistral model is the cheapest?
Mistral Nemo, at $0.029 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $1.67 a month on it.
Does Mistral discount cached prompts?
Yes. On Devstral 2 2512, cached input costs $0.04 per 1M tokens instead of $0.40, 90% less. Long, repeated system prompts and agent loops benefit most.
Is there a batch discount?
1 Mistral models have a batch price, typically half the normal rate, for jobs that can wait (up to 24 hours). See the Batch column below.
How do I track my Mistral spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real Mistral bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial