mistral-small-latest
- Input / 1M
- $0.06
- Output / 1M
- $0.18
- Cached input
- —
- Context
- 131K
A 1,000-token prompt costs $0.00006 to send. Token counts for Mistral models are estimated — approximated, because this family has no public tokenizer.
- Vision
- Tool calling
- Max output 131K
Priced closest to this
| Model | Provider | Input | Output | |
|---|---|---|---|---|
| mistral-small-3-2-2506 | Mistral | $0.06 | $0.18 | |
| gpt-5-nano | OpenAI | $0.05 | $0.40 | |
| gemma-7b-it | Groq | $0.05 | $0.08 | |
| llama-3.1-8b-instant | Groq | $0.05 | $0.08 | |
| mistral-7b-instruct | Perplexity | $0.07 | $0.28 | |
| mixtral-8x7b-instruct | Perplexity | $0.07 | $0.28 |