Mistral AI
Model lab · 21 models · also sold by 8 other providers · mistral.ai
Mistral AI models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Mistral Medium 3.5 Mistral AI · 262K | $1.5 | $7.5 | $1.5 / $7.5 | $3 | 262K | Lab list price | · |
| Mistral Small 4 Mistral AI · 262K | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 262K | Lab list price | · |
| Devstral 2 2512 Mistral AI · 262K | $0.4 | $2 | $0.4 / $2 | $0.8 | 262K | on Mistral AI (eu) | · |
| Ministral 3 14B 2512 Mistral AI · 262K | $0.2 | $0.2 | $0.2 / $0.2 | $0.2 | 262K | Lab list price | · |
| Ministral 3 3B 2512 Mistral AI · 131K | $0.1 | $0.1 | $0.1 / $0.1 | $0.1 | 131K | Lab list price | · |
| Ministral 3 8B 2512 Mistral AI · 262K | $0.15 | $0.15 | $0.15 / $0.15 | $0.15 | 262K | Lab list price | · |
| Mistral Large 3 2512 Mistral AI · 262K | $0.5 | $1.5 | $0.5 / $1.5 | $0.75 | 262K | Lab list price | · |
| Mistral Embed 2312 Mistral AI · 8K | $0.1 | Free | $0.1 / Free | $0.075 | 8K | Lab list price | · |
| Codestral Embed 2505 Mistral AI · 8K | $0.15 | Free | $0.15 / Free | $0.112 | 8K | Lab list price | · |
| Voxtral Small 24B 2507 Mistral AI · 33K | $0.1 | $0.3 | $0.1 / $0.3 | $0.15 | 33K | Lab list price | · |
| Mistral Medium 3.1 Mistral AI · 131K | $0.4 | $2 | $0.4 / $2 | $0.8 | 131K | Lab list price | · |
| Codestral 2508 Mistral AI · 256K | $0.3 | $0.9 | $0.3 / $0.9 | $0.45 | 256K | Lab list price | · |
| Mistral Small 3.2 24B Mistral AI · 256K | $0.075 | $0.2 | $0.075 / $0.2 | $0.106 | 256K | on DeepInfra (fp8) | · |
| Mistral Medium 3 Mistral AI · 131K | $0.4 | $2 | $0.4 / $2 | $0.8 | 131K | Lab list price | · |
| Mistral Small 3.1 24B Mistral AI · 128K | $0.351 | $0.555 | $0.351 / $0.555 | $0.402 | 128K | on Cloudflare Workers AI | · |
| Saba Mistral AI · 33K | $0.2 | $0.6 | $0.2 / $0.6 | $0.3 | 33K | Lab list price | · |
| Mistral Small 3 Mistral AI · 33K | $0.05 | $0.08 | $0.05 / $0.08 | $0.058 | 33K | on DeepInfra (fp8) | · |
| Mistral Large 2407 Mistral AI · 131K | $2 | $6 | $2 / $6 | $3 | 131K | Lab list price | · |
| Mistral Nemo Mistral AI · 131K | $0.018 | $0.03 | $0.018 / $0.03 | $0.021 | 131K | on DekaLLM (fp8) | · |
| Mixtral 8x22B Instruct Mistral AI · 66K | $2 | $6 | $2 / $6 | $3 | 66K | Lab list price | · |
| Mistral Large Mistral AI · 128K | $2 | $6 | $2 / $6 | $3 | 128K | Lab list price | · |
On other routes
| Model | In / out per 1M | Vs headline |
|---|---|---|
| Mistral Nemo DekaLLM, fp8, fp8 | $0.018 / $0.03Same vs headline | Same |
 Mistral NemoDeepInfra, fp8, fp8 | $0.019 / $0.03+4% vs headline | +4% |
 Mistral NemoParasail, fp8, fp8 | $0.03 / $0.03+43% vs headline | +43% |
| Mistral Small 3 DeepInfra, fp8, fp8 | $0.05 / $0.08Same vs headline | Same |
| Mistral Nemo Io Net, fp16, fp16 | $0.04 / $0.147+220% vs headline | +220% |
 Mistral NemoNovita AI, fp8, fp8 | $0.04 / $0.17+245% vs headline | +245% |
| Mistral Embed 2312 Mistral AI, zdr | $0.1 / FreeSame vs headline | Same |
| Mistral Embed 2312 Mistral AI, eu | $0.11 / Free+10% vs headline | +10% |
| Ministral 3 3B 2512 Mistral AI, zdr | $0.1 / $0.1Same vs headline | Same |
| Mistral Small 3.2 24B DeepInfra, fp8, fp8 | $0.075 / $0.2Same vs headline | Same |
| Ministral 3 3B 2512 Mistral AI, eu | $0.11 / $0.11+10% vs headline | +10% |
| Codestral Embed 2505 Mistral AI, zdr | $0.15 / FreeSame vs headline | Same |
| Codestral Embed 2505 Mistral AI, eu | $0.165 / Free+10% vs headline | +10% |
 Mistral Small 3.2 24BVenice, fp8, fp8 | $0.094 / $0.25+25% vs headline | +25% |
| Mistral Small 3.2 24B Parasail, bf16, bf16 | $0.09 / $0.3+34% vs headline | +34% |
| Ministral 3 8B 2512 Mistral AI, zdr | $0.15 / $0.15Same vs headline | Same |
| Mistral Nemo Mistral AI, eu | $0.15 / $0.15+614% vs headline | +614% |
| Voxtral Small 24B 2507 Mistral AI, zdr | $0.1 / $0.3Same vs headline | Same |
| Mistral Small 3.2 24B Mistral AI, eu | $0.1 / $0.3+41% vs headline | +41% |
| Ministral 3 8B 2512 Mistral AI, eu | $0.165 / $0.165+10% vs headline | +10% |
About Mistral AI
Mistral AI SAS is a French artificial intelligence (AI) company headquartered in Paris. Founded in 2023, it develops large language models (LLMs).
Batch: Batch processing, for high-volume work, reduces the price by 50%
Caching: cached input tokens reduce input cost by up to 90% for repeated prompts
Mistral AI on the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.