D
DeepSeek: deepseek-v3.1
deepseek-v3.1
163.8K context163.8K outReasoningToolsFilesStructured
Released Aug 21, 2025Knowledge cutoff Jun 2025Updated Oct 29, 2026
A hybrid-inference flagship MoE model (671B total, 37B active). It bridges the gap between speed and logic by supporting both Thinking and Non-Thinking modes in a single model, featuring enhanced tool-calling and a 128k context window.
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
$0.01/ 1M tokens95% off
Output price
$0.05/ 1M tokens95% off
Context window 32.8K tokensCompatible endpoints openaiVendor DeepSeekProvider Routerah
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 | Not sent by default |
| include_reasoning | All providers | - |
| max_tokens | All providers | - |
| reasoning | All providers | - |
| response_format | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | Not sent by default |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | - |
| top_p | All providers | Not sent by default |