litellm - 💡(How to fix) Fix [Bug]: "When using v0.21.0 to launch deepseek-v4-flashwith thinking mode enabled, the reasoning_contentfield is not returned."

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Root Cause

"messages": [
    {
      "role": "user",
      "content": "9.11 and 9.8, which is greater?"
    }
  ],
  "reasoning_effort": "medium",
  "extra_body": {
    "thinking": {
      "type": "enabled"
    }
  }。response:"model": "/data/DeepSeek-V4-Flash",
	"choices": [
		{
			"index": 0,
			"message": {
				"role": "assistant",
				"content": "This is a trick question that often trips people up because of how we read numbers.\n\nWhile 9.11 is a larger *number* in terms of digits (eleven vs. eight), **9.8 is greater in value.**\n\nHere’s why:\n*   9.8 is the same as 9.80.\n*   9.80 is greater than 9.11.\n\nSo, **9.8 is greater than 9.11**.",
				"refusal": null,
				"annotations": null,
				"audio": null,
				"function_call": null,
				"tool_calls": [],
				"reasoning": null
			},
			"logprobs": null,
			"finish_reason": "stop",
			"stop_reason": null,
			"token_ids": null,
			"routed_experts": null
		}
	],
	"service_tier": null,
	"system_fingerprint": "vllm-0.21.0-dp4-ep-6873ddae",

Code Example

"messages": [
    {
      "role": "user",
      "content": "9.11 and 9.8, which is greater?"
    }
  ],
  "reasoning_effort": "medium",
  "extra_body": {
    "thinking": {
      "type": "enabled"
    }
  }。response:"model": "/data/DeepSeek-V4-Flash",
	"choices": [
		{
			"index": 0,
			"message": {
				"role": "assistant",
				"content": "This is a trick question that often trips people up because of how we read numbers.\n\nWhile 9.11 is a larger *number* in terms of digits (eleven vs. eight), **9.8 is greater in value.**\n\nHere’s why:\n*   9.8 is the same as 9.80.\n*   9.80 is greater than 9.11.\n\nSo, **9.8 is greater than 9.11**.",
				"refusal": null,
				"annotations": null,
				"audio": null,
				"function_call": null,
				"tool_calls": [],
				"reasoning": null
			},
			"logprobs": null,
			"finish_reason": "stop",
			"stop_reason": null,
			"token_ids": null,
			"routed_experts": null
		}
	],
	"service_tier": null,
	"system_fingerprint": "vllm-0.21.0-dp4-ep-6873ddae",
RAW_BUFFERClick to expand / collapse

Check for existing issues

  • I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

"I noticed this issue while comparing the behavior with the official DeepSeek API documentation."

Steps to Reproduce

"I noticed this while comparing the behavior with the official DeepSeek API documentation."

Relevant log output

"messages": [
    {
      "role": "user",
      "content": "9.11 and 9.8, which is greater?"
    }
  ],
  "reasoning_effort": "medium",
  "extra_body": {
    "thinking": {
      "type": "enabled"
    }
  }。response:"model": "/data/DeepSeek-V4-Flash",
	"choices": [
		{
			"index": 0,
			"message": {
				"role": "assistant",
				"content": "This is a trick question that often trips people up because of how we read numbers.\n\nWhile 9.11 is a larger *number* in terms of digits (eleven vs. eight), **9.8 is greater in value.**\n\nHere’s why:\n*   9.8 is the same as 9.80.\n*   9.80 is greater than 9.11.\n\nSo, **9.8 is greater than 9.11**.",
				"refusal": null,
				"annotations": null,
				"audio": null,
				"function_call": null,
				"tool_calls": [],
				"reasoning": null
			},
			"logprobs": null,
			"finish_reason": "stop",
			"stop_reason": null,
			"token_ids": null,
			"routed_experts": null
		}
	],
	"service_tier": null,
	"system_fingerprint": "vllm-0.21.0-dp4-ep-6873ddae",

What part of LiteLLM is this about?

Docs

What LiteLLM version are you on ?

v1.53.1

Twitter / LinkedIn details

No response

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING