All Models
DeepSeek Chat V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 TensorX | deepseek/deepseek-chat-v3.1 | $0.20/MTok | $0.80/MTok | 164K | 163.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output