docs/en/models/deepseek.mdx
DeepSeek is one of the default recommended vendors in Agent mode, focused on cost-effective text chat and task planning.
{
"model": "deepseek-v4-flash",
"deepseek_api_key": "YOUR_API_KEY"
}
| Parameter | Description |
|---|---|
model | Supports deepseek-v4-flash (Default), deepseek-v4-pro |
deepseek_api_key | Create one on the DeepSeek Platform |
deepseek_api_base | Optional, defaults to https://api.deepseek.com/v1. Can be changed to a third-party proxy |
| Model | Use Case |
|---|---|
deepseek-v4-flash | Default recommended; fast and low cost |
deepseek-v4-pro | Smarter; better for complex tasks |
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.
Controlled by the global enable_thinking config, and can also be toggled from the Web Console's configuration page:
{
"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.Under thinking mode, reasoning_effort controls reasoning intensity:
{
"enable_thinking": true,
"reasoning_effort": "high"
}
| Value | Use Case |
|---|---|
high (Default) | Day-to-day Agent tasks; balanced reasoning and speed |
max | Complex 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.
temperature, top_p, presence_penalty, and frequency_penalty are ignored by the server (without errors). CowAgent automatically skips them.reasoning_content. CowAgent handles this automatically, so toggling thinking mode across turns will not cause errors.