Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Specification
most-agreed values
Context
33K
Max output
16K
Released
2023-12-10
Knowledge cutoff
—
Retires
2025-04-30
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
free
Output
free
Cache read
$0.50
Cache write
$0.50
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nvidia | free | free | — | — | 33K | 16K | — |
| perplexity | $0.07 | $0.28 | — | — | 4K | 4K | — |
| deepinfra | $0.40 | $0.40 | — | — | 33K | 33K | — |
| databricks | $0.50 | $1.00 | $0.50 | $0.50 | 4K | 4K | 2025-04-30 |
| fireworks_ai | $0.50 | $0.50 | — | — | 33K | 33K | — |
| bedrock | $0.59 $0.45 | $0.91 $0.70 | — | — | 32K | 8K | — |
| together_ai | $0.60 | $0.60 | — | — | — | — | 2026-04-16 |
More from Mistral
most-hosted first