Compare models
Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.
| Model | Codestral Embed 2505 Mistral AI · Embedding | Mistral Embed 2312 Mistral AI · Embedding |
|---|---|---|
| Overview | ||
| Released | - | - |
| Status | Current | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 1 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Mistral AI | Mistral AI |
| Input | $0.15 | $0.10 |
| Output | - | - |
| Cached input | $0.015 | $0.01 |
| Batch input / output | - | - |
| Cheapest anywhere input / output | $0.15 / - Mistral AI | $0.10 / - Mistral AI |
| Monthly bill · at the price above, 30 days, with each workload's cache and batch use | ||
| Chat assistant 5,000 a day, 2K in, 500 out | $32.85 | $21.90 |
| RAG over documents 2,000 a day, 8K in, 600 out | $39.60 | $26.40 |
| Coding agent 1,000 a day, 40K in, 2K out | $66.60 | $44.40 |
| Overnight batch 20,000 a day, 4K in, 400 out | $360 | $240 |
| Limits | ||
| Context window | 8K tokens | 8K tokens |
| Max output | - | - |
| Capabilities | ||
| Takes in | Text | Text |
| Produces | Embeddings | Embeddings |
| Effort settings as listed by the source | - | - |