M
Mistral: mistral-large-4
mistral-large-4
1M context262.1K outReasoningToolsVisionFilesCacheStructuredPrefill
Released Oct 6, 2026Knowledge cutoff Nov 2024Updated Oct 6, 2026
Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work
Mode chatTokenizer Mistral
Inputs used for the providers' own purposes
At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.
Read the privacy policyPricing
Input price
$2.72/ 1M tokens
Output price
$8.16/ 1M tokens
Compatible endpoints openaiVendor Mistral
Uptime
Performance
Loading performance data...
Usage & Ranking
Loading usage...
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | All providers | - |
| max_tokens | All providers | - |
| presence_penalty | All providers | - |
| response_format | All providers | - |
| seed | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | 0.3 |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_p | All providers | - |