DeepSeek reasoner (R1 thinking mode)
deepseek_reasonGenerates explicit chain-of-thought reasoning before answering hard math, logic, debugging, and multi-step planning prompts, returning the reasoning trace and final answer separately.
Instructions
Send a prompt to deepseek-reasoner, which produces an explicit chain of thought before its answer. Best for hard maths, logic, debugging and multi-step planning. Returns the reasoning trace and the final answer separately. Sampling parameters are ignored by this model and are dropped automatically.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "deepseek_reason"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| stop | No | Up to 16 stop sequences. A single string is also accepted. | |
| extra | No | Arbitrary extra request-body fields, merged last so they override everything else. The escape hatch for any API parameter this server does not model yet. | |
| model | No | Override the model id for this call. | |
| tools | No | Function-calling definitions, passed to the API verbatim. Each item is { type: 'function', function: { name, description, parameters } }. | |
| top_p | No | Nucleus sampling, 0-1. Ignored by deepseek-reasoner. | |
| prompt | No | The user message. Use this for one-shot calls. | |
| stream | No | Stream from the API and return the assembled result. Useful for very long outputs that would otherwise hit an idle timeout. | |
| system | No | System instruction. | |
| logprobs | No | Return log probabilities. deepseek-chat only. | |
| messages | No | Full message array, OpenAI-compatible. Use this instead of `prompt` when you need multi-turn control. Roles: system, user, assistant, tool. | |
| json_mode | No | Shorthand for response_format { type: 'json_object' }. Your prompt must mention JSON and should show an example. | |
| max_tokens | No | Maximum output tokens. Omit for the server-side maximum (8192 for deepseek-chat, 65536 for deepseek-reasoner). No client-side cap is applied. | |
| session_id | No | Conversation key. Prior turns under this id are prepended automatically and this turn is appended, giving true multi-turn memory across tool calls. | |
| timeout_ms | No | Per-call timeout override in milliseconds. | |
| temperature | No | 0.0-2.0. DeepSeek's own guidance: 0.0 for code and maths, 1.0 for general conversation and data analysis, 1.3 for creative writing. Ignored by deepseek-reasoner. | |
| tool_choice | No | 'auto', 'none', 'required', or { type: 'function', function: { name } }. | |
| raw_response | No | Return the complete unmodified API JSON instead of formatted text. | |
| top_logprobs | No | 0-20, requires logprobs. deepseek-chat only. | |
| include_usage | No | Append the token-usage and cache-hit footer. Default true. | |
| presence_penalty | No | -2.0 to 2.0. Ignored by deepseek-reasoner. | |
| frequency_penalty | No | -2.0 to 2.0. Ignored by deepseek-reasoner. | |
| include_reasoning | No | Include the chain-of-thought block in the result. Default true for deepseek-reasoner. |