`deepseek-v4-pro` model ID is not recognized as a thinking model, causing `reasoning_content` errors even with `interleaved` configured

[ruichenrui]

Description

Config that fails

{
  "provider": {
    "deepseek": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "DeepSeek",
      "options": {
        "baseURL": "https://api.deepseek.com",
        "apiKey": "<key>"
      },
      "models": {
        "deepseek-v4-pro": {
          "name": "DeepSeek-V4-Pro",
          "limit": { "context": 1048576, "output": 262144 },
          "interleaved": { "field": "reasoning_content" },
          "options": {
            "reasoningEffort": "max",
            "thinking": { "type": "enabled" }
          }
        }
      }
    }
  }
}

**Error**

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

**Workaround that works**

Changing the model key from deepseek-v4-pro to deepseek-reasoner (with identical options) resolves the error:
"deepseek-reasoner": {
  "name": "DeepSeek-V4-Pro",
  "interleaved": { "field": "reasoning_content" },
  ...
}

**Expected behavior**

deepseek-v4-pro should be recognized as a thinking/reasoning model and handle reasoning_content correctly when interleaved is configured, just like deepseek-reasoner.

**Reference**

DeepSeek API docs list deepseek-v4-pro as the official model identifier for V4 Pro: https://api-docs.deepseek.com/

### Plugins

_No response_

### OpenCode version

1.14.21

### Steps to reproduce

_No response_

### Screenshot and/or share link

_No response_

### Operating System

_No response_

### Terminal

_No response_

[github-actions]

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

• The reasoning_content in the thinking mode must be passed back to the API. #24083: Same error message — reasoning_content in thinking mode must be passed back to the API, also involving DeepSeek
• Adapting to the New DeepSeek Model #24092: Related request to support the new DeepSeek V4 model

If your issue is distinct (e.g., specifically about the model ID not being recognized as a reasoning model when using a custom key like deepseek-v4-pro vs deepseek-reasoner), feel free to clarify so it can be tracked separately.

[Svtter]

This post solved this problem.

[ruichenrui]

Thanks for checking. After reviewing both issues, mine is distinct:

• The reasoning_content in the thinking mode must be passed back to the API. #24083: Only shows the error message without config details or root-cause analysis.
• Adapting to the New DeepSeek Model #24092: A generic request to "adapt to DeepSeek V4" with no technical specifics.
  My report provides verified workarounds that prove this is a bug in model ID recognition, not a missing feature.
  Workaround 1: Using the legacy model ID deepseek-reasoner with @ai-sdk/openai-compatible works with identical config.
  Workaround 2 (via community member @Svtter): Switch to @ai-sdk/anthropic with DeepSeek's Anthropic-compatible endpoint:

{
  "provider": {
    "deepseek": {
      "npm": "@ai-sdk/anthropic",
      "name": "DeepSeek",
      "options": {
        "baseURL": "https://api.deepseek.com/anthropic",
        "apiKey": "<apikey>"
      },
      "models": {
        "deepseek-v4-pro": {
          "name": "DeepSeek-V4-Pro",
          "limit": { "context": 1048576, "output": 262144 },
          "options": {
            "thinking": { "type": "enabled", "budgetTokens": 8192 }
          }
        }
      }
    }
  }
}
Results:
- @ai-sdk/openai-compatible + deepseek-v4-pro = Broken
- @ai-sdk/openai-compatible + deepseek-reasoner = Works
- @ai-sdk/anthropic + deepseek-v4-pro = Works
This strongly suggests the bug is specifically in how OpenCode maps deepseek-v4-pro when using @ai-sdk/openai-compatible, not a general lack of V4 support.

[ruichenrui]

Update: Tested the @ai-sdk/anthropic workaround mentioned above, but it also fails with a similar error.
Config used:

{
  "provider": {
    "deepseek": {
      "npm": "@ai-sdk/anthropic",
      "name": "DeepSeek",
      "options": {
        "baseURL": "https://api.deepseek.com/anthropic",
        "apiKey": "{env:DEEPSEEK}"
      },
      "models": {
        "deepseek-v4-pro": {
          "name": "DeepSeek-V4-Pro",
          "limit": {
            "context": 1048576,
            "output": 262144
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 81920
            }
          }
        }
      }
    }
  }
}
Error:
Bad Request: {"error":{"message":"The content[].thinking in the thinking mode must be passed back to the API.","type":"invalid_request_error","param":null,"code":"invalid_request_error"}}
This confirms that the issue is not specific to the OpenAI-compatible protocol. Both @ai-sdk/openai-compatible and @ai-sdk/anthropic paths fail with deepseek-v4-pro because OpenCode does not correctly preserve and forward the model's reasoning/thinking content back to the API on subsequent turns.

[Small-tailqwq]

相同的问题

使用配置如下：

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

Bad Request: {"error":{"message":"The `content[].thinking` in the thinking mode must be passed back to the API.","type":"invalid_request_error","param":null,"code":"invalid_request_error"}}