[Solution] How to enable DeepSeek V4 thinking mode in OpenCode using Anthropic API

Problem

When using DeepSeek V4 with thinking mode enabled in OpenCode, you may encounter this error:

The reasoning_content in the thinking mode must be passed back to the API

This happens because:

DeepSeek V4 returns reasoning_content (thinking process) in addition to content (final answer)
In multi-turn conversations with tool calls, reasoning_content must be passed back to the API
The @ai-sdk/openai-compatible package doesn't preserve and pass back reasoning_content

Solution

Use DeepSeek's Anthropic-compatible API instead of the OpenAI-compatible one. The @ai-sdk/anthropic package natively supports reasoning mode (Claude extended thinking).

Configuration

Edit ~/.config/opencode/opencode.json:

"deepseekv4": {
  "npm": "@ai-sdk/anthropic",
  "name": "DeepSeek",
  "options": {
    "baseURL": "https://api.deepseek.com/anthropic",
    "apiKey": "your-deepseek-api-key"
  },
  "models": {
    "deepseek-v4-pro": {
      "name": "DeepSeek-V4-Pro",
      "limit": {
        "context": 1048576,
        "output": 262144
      },
      "options": {
        "thinking": {
          "type": "enabled",
          "budgetTokens": 8192
        }
      }
    }
  }
}

Key Changes

npm: Change from @ai-sdk/openai-compatible to @ai-sdk/anthropic
baseURL: Change from https://api.deepseek.com to https://api.deepseek.com/anthropic
thinking.type: Set to "enabled" to activate thinking mode

Why This Works

DeepSeek provides two API formats: OpenAI-compatible and Anthropic-compatible
The Anthropic SDK has native support for reasoning mode (used by Claude's extended thinking)
By switching to the Anthropic API format, OpenCode can properly handle reasoning_content without code changes

Usage

After restarting OpenCode, DeepSeek V4 will work with thinking mode enabled. You'll see the reasoning process in the model's responses.

References

Community solution article: https://svtter.cn/p/如何解决-opencode-中-deepseek-模型的-reasoning-问题/
DeepSeek API docs: https://api-docs.deepseek.com/zh-cn/

Tested Environment

OpenCode version: Latest (as of 2026-04-24)
DeepSeek API: v4-pro
OS: Windows 11

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

This issue doesn't use one of the required templates (Bug Report, Feature Request, or Question). It appears to be a workaround/solution post, which doesn't fit the issue tracker format. If you want to share this as a bug report about missing reasoning_content support, please use the Bug Report template. If you're requesting a fix, use the Feature Request template (with a [FEATURE]: title prefix).

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

This issue might be a duplicate of existing issues. Please check:

Support DeepSeek V4 Thinking Mode with reasoning_content handling #24114: Support DeepSeek V4 Thinking Mode with reasoning_content handling
DeepSeek thinking mode: reasoning_content must be passed back to API on conversation continuation #24104: DeepSeek thinking mode: reasoning_content must be passed back to API on conversation continuation
deepseek-v4-pro model ID is not recognized as a thinking model, causing reasoning_content errors even with interleaved configured #24097: deepseek-v4-pro model ID not recognized as thinking model, causing reasoning_content errors
Missing reasoning_content field in the assistant message for DeepSeek API implementation #17523: Missing reasoning_content field in assistant message for DeepSeek API implementation
Interleaved reasoning_content lost for non-Claude models on Anthropic SDK #14638: Interleaved reasoning_content lost for non-Claude models on Anthropic SDK

If you believe this was flagged incorrectly, please let a maintainer know.

@ai-sdk/anthropic still fails sometimes. here's a better workaround i'm using now:
using transformRequestBody to add all missing strings

      if (body.messages) {
        for (const msg of body.messages) {
          if (msg.role === 'assistant') {
            if (msg.tool_calls && msg.tool_calls.length > 0) {
              if (!msg.content) {
                msg.content = 'call tool';
              }
              if (!msg.reasoning_content) {
                msg.reasoning_content = 'call tool';
              }
            } else {
              if (!msg.content) {
                msg.content = 'wait user input';
              }
              if (!msg.reasoning_content) {
                msg.reasoning_content = 'answer';
              }
            }
          }
        }
      }

使用和token记录

@ai-sdk/anthropic still fails sometimes. here's a better workaround i'm using now:@ai-SDK/Anthropic 有时还是会失败。这里有我现在用的更好的变通方法： using transformRequestBody to add all missing strings使用 transformRequestBody 添加所有缺失字符串
  if (body.messages) {
    for (const msg of body.messages) {
      if (msg.role === 'assistant') {
        if (msg.tool_calls && msg.tool_calls.length > 0) {
          if (!msg.content) {
            msg.content = 'call tool';
          }
          if (!msg.reasoning_content) {
            msg.reasoning_content = 'call tool';
          }
        } else {
          if (!msg.content) {
            msg.content = 'wait user input';
          }
          if (!msg.reasoning_content) {
            msg.reasoning_content = 'answer';
          }
        }
      }
    }
  }

是的这个方案更佳

Closing to recreate with proper template format.

在openclaw调用deepseekV4的时候，我也遇到了；openclaw.json里应该怎么改？

上面有

@ai-sdk/anthropic still fails sometimes. here's a better workaround i'm using now: using transformRequestBody to add all missing strings

  if (body.messages) {
    for (const msg of body.messages) {
      if (msg.role === 'assistant') {
        if (msg.tool_calls && msg.tool_calls.length > 0) {
          if (!msg.content) {
            msg.content = 'call tool';
          }
          if (!msg.reasoning_content) {
            msg.reasoning_content = 'call tool';
          }
        } else {
          if (!msg.content) {
            msg.content = 'wait user input';
          }
          if (!msg.reasoning_content) {
            msg.reasoning_content = 'answer';
          }
        }
      }
    }
  }

What does that mean?? where do you use that? i defined my plugin but it doesn't work; can you please clarify what you mean by this code???

你发给ai吧,我已经开始用pi了,很久没用opencode了不记得,你有web_search吗,直接把链接发过去,没有就直接粘贴吧,应该ai可以改的

哈哈，挺久前的问题了；AI几天一个样，我现在都用的codex、cc、hermes了

Navigation Menu

Repository navigation

[Solution] How to enable DeepSeek V4 thinking mode in OpenCode using Anthropic API #24122

Problem

Solution

Configuration

Key Changes

Why This Works

Usage

References

Tested Environment

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

[Solution] How to enable DeepSeek V4 thinking mode in OpenCode using Anthropic API #24122

Description

Problem

Solution

Configuration

Key Changes

Why This Works

Usage

References

Tested Environment

Activity

github-actions commented on Apr 24, 2026

AutumnSun1996 commented on Apr 24, 2026

LieGeee commented on Apr 24, 2026

LieGeee commented on Apr 24, 2026

LieGeee commented on Apr 24, 2026

CycSpring commented on Apr 24, 2026

LieGeee commented on Apr 24, 2026

arjunp1120 commented on May 29, 2026

LieGeee commented on May 29, 2026

CycSpring commented on Jun 1, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions