devstral-medium-latest
- Input / 1M
- $0.40
- Output / 1M
- $2.00
- Cached input
- —
- Context
- 256K
A 1,000-token prompt costs $0.00040 to send. Token counts for Mistral models are estimated — approximated, because this family has no public tokenizer.
- Tool calling
- Max output 256K
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| qwen-3-32b | Cerebras | $0.40 | $0.80 | |
| gpt-4.1-mini | OpenAI | $0.40 | $1.60 | |
| devstral-2512 | Mistral | $0.40 | $2.00 | |
| devstral-latest | Mistral | $0.40 | $2.00 | |
| devstral-medium-2507 | Mistral | $0.40 | $2.00 | |
| mistral-medium-2505 | Mistral | $0.40 | $2.00 |