Flagship Mistral model for advanced reasoning, coding, and multilingual work
Specification
most-agreed values
Context
262K
Max output
256K
Released
2025-12-25
Knowledge cutoff
2025-01
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.00
Output
$3.00
Cache read
$0.50
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nvidia | free | free | — | — | 262K | 262K | — |
| amazon-bedrock | $0.50 | $1.50 | — | — | 256K | 8K | — |
| bedrock_converse | $0.50 | $1.50 | — | — | 128K | 8K | — |
| nano-gpt | $1.00 | $3.00 | $0.50 | — | 262K | 256K | — |
Other listings of this model
this page is one of them
The corpus files Mistral Large 3 675B under several keys. This page is the mistral-large-3-675b-instruct listing. The full record — every host, every price and every benchmark score — is on the main Mistral Large 3 675B page.
More from Mistral
most-hosted first