Back to Chatgpt On Wechat

DeepSeek

docs/en/models/deepseek.mdx

2.0.92.5 KB
Original Source

DeepSeek is one of the default recommended vendors in Agent mode, focused on cost-effective text chat and task planning.

Text Chat

json
{
  "model": "deepseek-v4-flash",
  "deepseek_api_key": "YOUR_API_KEY"
}
ParameterDescription
modelSupports deepseek-v4-flash (Default), deepseek-v4-pro
deepseek_api_keyCreate one on the DeepSeek Platform
deepseek_api_baseOptional, defaults to https://api.deepseek.com/v1. Can be changed to a third-party proxy

Model Selection

ModelUse Case
deepseek-v4-flashDefault recommended; fast and low cost
deepseek-v4-proSmarter; better for complex tasks

Thinking Mode

The V4 series (deepseek-v4-flash / deepseek-v4-pro) supports an explicit "thinking mode": before producing the final answer, the model emits a chain of thought (reasoning_content) to improve answer quality.

Toggle

Controlled by the global enable_thinking config, and can also be toggled from the Web Console's configuration page:

json
{
  "enable_thinking": true
}
  • true: the model thinks before answering across all channels. The Web Console displays the thinking process; IM channels (WeChat / WeCom / DingTalk / Feishu) do not show it but still get better answers.
  • false: thinking is disabled, responses are faster, and time-to-first-token is lower.

Reasoning Effort

Under thinking mode, reasoning_effort controls reasoning intensity:

json
{
  "enable_thinking": true,
  "reasoning_effort": "high"
}
ValueUse Case
high (Default)Day-to-day Agent tasks; balanced reasoning and speed
maxComplex coding, long-horizon planning, strictly constrained tasks; deeper reasoning but more time and output tokens

reasoning_effort only takes effect when enable_thinking is true; it is ignored automatically when the model does not support thinking mode.

Behavior Notes

  • Sampling parameters: in thinking mode, temperature, top_p, presence_penalty, and frequency_penalty are ignored by the server (without errors). CowAgent automatically skips them.
  • Multi-turn tool calls: when the history contains tool calls, DeepSeek requires every assistant message to include reasoning_content. CowAgent handles this automatically, so toggling thinking mode across turns will not cause errors.
<Tip> `deepseek-v4-flash` is used by default; switch to `deepseek-v4-pro` for complex tasks; enable `enable_thinking` when deep reasoning is needed. </Tip>