Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000005 | $0.500 |
| completion | 0.0000015 | $1.50 |
| input_cache_read | 0.00000005 | $0.050 |
{
"temperature": 0.0645,
"top_p": null,
"frequency_penalty": null
}