litellm - 💡(How to fix) Fix [Bug]: response API wrong model name resolution [1 participants]

litellm2026-04-29 12:19:08

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.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

BerriAI/litellm#26773•Fetched 2026-04-30 06:20:09

View on GitHub

Comments

Participants

Timeline

Reactions

Author

Heshmatkhah

Participants

Heshmatkhah

Timeline (top)

labeled ×3

Error Message

{ "error": { "message": "litellm.BadRequestError: OpenrouterException - {"error":{"message":"openrouter/openai/gpt-4o is not a valid model ID","code":400},"user_id":"user_33T2s3poJxTY0aRaCzsDNON2Xb1"}. Received Model Group=mymodel\nAvailable Model Group Fallbacks=None", "type": null, "param": null, "code": "400" } }

Code Example

model_list:
  - model_name: openrouter/*
    litellm_params:
      model: openrouter/*
      api_base: https://openrouter.ai/api/v1
      api_key: os.environ/OPEN_ROUTER_API_KEY

  - model_name: mymodel
    litellm_params:
      model: openrouter/openai/gpt-4o
      api_key: os.environ/OPEN_ROUTER_API_KEY

# I also tested this configuration and observed the same behavior:
#router_settings:
#  model_group_alias:
#    "mymodel": "openrouter/openai/gpt-4o"

---

curl -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer sk-123' \
  -q -L -X POST 'https://llm.example.com/chat/completions' \
  -d '{
    "model": "mymodel",
    "messages": [
      {
        "role": "system",
        "content": "You are an LLM named MyModel"
      },
      {
        "role": "user",
        "content": "what is your name?"
      }
    ]
  }' | jq

---

{
  "id": "gen-1777462401-PcgnzN9w859JYuFh3g7h",
  "created": 1777462401,
  "model": "mymodel",
  "object": "chat.completion",
  "system_fingerprint": "fp_c9e874ca3a",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "I am MyModel, your language model assistant. How can I help you today?",
        "role": "assistant",
        "provider_specific_fields": {
          "reasoning": null,
          "refusal": null
        }
      },
      "provider_specific_fields": {
        "native_finish_reason": "stop"
      }
    }
  ],
  "usage": {
    "completion_tokens": 18,
    "prompt_tokens": 25,
    "total_tokens": 43,
    "completion_tokens_details": {
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "image_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0,
      "video_tokens": 0,
      "cache_write_tokens": 0
    },
    "cost": 0.0002425,
    "is_byok": false,
    "cost_details": {
      "upstream_inference_cost": 0.0002425,
      "upstream_inference_prompt_cost": 6.25e-05,
      "upstream_inference_completions_cost": 0.00018
    }
  },
  "provider": "OpenAI"
}

---

curl -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer sk-123' \
  -q -L -X POST 'https://llm.example.com/chat/completions' \
  -d '{
    "model": "mymodel",
    "input": [
      {
        "role": "system",
        "content": [
          {
            "type": "input_text",
            "text": "You are an LLM named MyModel"
          }
        ]
      },
      {
        "role": "user",
        "content": "what is your name?"
      }
    ],
    "store": false,
    "temperature": 0.5
  }' | jq

---

{
  "error": {
    "message": "litellm.BadRequestError: OpenrouterException - {\"error\":{\"message\":\"openrouter/openai/gpt-4o is not a valid model ID\",\"code\":400},\"user_id\":\"user_33T2s3poJxTY0aRaCzsDNON2Xb1\"}. Received Model Group=mymodel\nAvailable Model Group Fallbacks=None",
    "type": null,
    "param": null,
    "code": "400"
  }
}

---

openrouter/openai/gpt-4o is not a valid model ID

---

openrouter/openai/gpt-4o is not a valid model ID

---

litellm-1  | 11:33:21 - LiteLLM:DEBUG: utils.py:481 - Final returned optional params: {'stream': False, 'max_retries': 0, 'extra_body': {}}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:538 - self.optional_params: {'stream': False, 'max_retries': 0}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: utils.py:5507 - checking potential_model_names in litellm.model_cost: {'split_model': 'openai/gpt-4o', 'combined_model_name': 'openrouter/openai/gpt-4o', 'stripped_model_name': 'openai/gpt-4o', 'combined_stripped_model_name': 'openrouter/openai/gpt-4o', 'custom_llm_provider': 'openrouter'}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:1131 -
litellm-1  |
litellm-1  | POST Request Sent from LiteLLM:
litellm-1  | curl -X POST \
litellm-1  | https://openrouter.ai/api/v1/chat/completions \
litellm-1  | -H 'HTTP-Referer: https://litellm.ai' -H 'X-Title: liteLLM' -H 'Authorization: Be****57' -H 'Content-Type: application/json' \
litellm-1  | -d '{'model': 'openai/gpt-4o', 'messages': [{'role': 'system', 'content': 'You are an LLM named MyModel'}, {'role': 'user', 'content': 'what is your name?'}], 'stream': False, 'usage': {'include': True}}'
litellm-1  |
litellm-1  |
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:1204 - RAW RESPONSE:

---

litellm-1  | 11:33:40 - LiteLLM:DEBUG: llm_http_handler.py:2238 - Creating HTTP client for responses API with shared_session: 140659107816384
litellm-1  | 11:33:40 - LiteLLM:DEBUG: litellm_logging.py:1131 -
litellm-1  |
litellm-1  | POST Request Sent from LiteLLM:
litellm-1  | curl -X POST \
litellm-1  | https://openrouter.ai/api/v1/responses \
litellm-1  | -H 'Authorization: Be****34' \
litellm-1  | -d '{'model': 'openrouter/openai/gpt-4o', 'input': [{'role': 'system', 'content': [{'type': 'input_text', 'text': 'You are an LLM named MyModel'}]}, {'content': 'what is your name?', 'role': 'user'}], 'store': False, 'temperature': 0.5}'
litellm-1  |
litellm-1  |

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?

Hi, thank you for your great app.

The Responses API (/v1/responses) does not use the correct model name when using an alias.

I have the following configuration:

model_list:
  - model_name: openrouter/*
    litellm_params:
      model: openrouter/*
      api_base: https://openrouter.ai/api/v1
      api_key: os.environ/OPEN_ROUTER_API_KEY

  - model_name: mymodel
    litellm_params:
      model: openrouter/openai/gpt-4o
      api_key: os.environ/OPEN_ROUTER_API_KEY

# I also tested this configuration and observed the same behavior:
#router_settings:
#  model_group_alias:
#    "mymodel": "openrouter/openai/gpt-4o"

Assume the following two curl requests.

Using /chat/completions:

curl -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer sk-123' \
  -q -L -X POST 'https://llm.example.com/chat/completions' \
  -d '{
    "model": "mymodel",
    "messages": [
      {
        "role": "system",
        "content": "You are an LLM named MyModel"
      },
      {
        "role": "user",
        "content": "what is your name?"
      }
    ]
  }' | jq

It return this response:

{
  "id": "gen-1777462401-PcgnzN9w859JYuFh3g7h",
  "created": 1777462401,
  "model": "mymodel",
  "object": "chat.completion",
  "system_fingerprint": "fp_c9e874ca3a",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "I am MyModel, your language model assistant. How can I help you today?",
        "role": "assistant",
        "provider_specific_fields": {
          "reasoning": null,
          "refusal": null
        }
      },
      "provider_specific_fields": {
        "native_finish_reason": "stop"
      }
    }
  ],
  "usage": {
    "completion_tokens": 18,
    "prompt_tokens": 25,
    "total_tokens": 43,
    "completion_tokens_details": {
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "image_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0,
      "video_tokens": 0,
      "cache_write_tokens": 0
    },
    "cost": 0.0002425,
    "is_byok": false,
    "cost_details": {
      "upstream_inference_cost": 0.0002425,
      "upstream_inference_prompt_cost": 6.25e-05,
      "upstream_inference_completions_cost": 0.00018
    }
  },
  "provider": "OpenAI"
}

Using /v1/responses

curl -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer sk-123' \
  -q -L -X POST 'https://llm.example.com/chat/completions' \
  -d '{
    "model": "mymodel",
    "input": [
      {
        "role": "system",
        "content": [
          {
            "type": "input_text",
            "text": "You are an LLM named MyModel"
          }
        ]
      },
      {
        "role": "user",
        "content": "what is your name?"
      }
    ],
    "store": false,
    "temperature": 0.5
  }' | jq

It return this error:

{
  "error": {
    "message": "litellm.BadRequestError: OpenrouterException - {\"error\":{\"message\":\"openrouter/openai/gpt-4o is not a valid model ID\",\"code\":400},\"user_id\":\"user_33T2s3poJxTY0aRaCzsDNON2Xb1\"}. Received Model Group=mymodel\nAvailable Model Group Fallbacks=None",
    "type": null,
    "param": null,
    "code": "400"
  }
}

As shown above, unlike /chat/completions, the /v1/responses endpoint does not correctly resolve the mymodel alias to the OpenRouter model. Instead, it sends openrouter/openai/gpt-4o as the model ID to OpenRouter, which causes OpenRouter to reject the request with:

openrouter/openai/gpt-4o is not a valid model ID

Steps to Reproduce

Set and alias to a model using ether model_list.model_name or router_settings.model_group_alias
Use that model in /chat/completions API
Use that model in /v1/responses API

Expected behavior:

/v1/responses should resolve and route aliases in the same way as /chat/completions.

Actual behavior:

/v1/responses appears to pass the internal LiteLLM/OpenRouter-prefixed model name directly to OpenRouter, causing the request to fail.

Relevant log output

The logs shows that, unlike /chat/completions, the /v1/responses endpoint does not correctly resolve the mymodel alias to the OpenRouter model. Instead, it sends openrouter/openai/gpt-4o as the model ID to OpenRouter, which causes OpenRouter to reject the request with:

openrouter/openai/gpt-4o is not a valid model ID

/chat/completions

litellm-1  | 11:33:21 - LiteLLM:DEBUG: utils.py:481 - Final returned optional params: {'stream': False, 'max_retries': 0, 'extra_body': {}}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:538 - self.optional_params: {'stream': False, 'max_retries': 0}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: utils.py:5507 - checking potential_model_names in litellm.model_cost: {'split_model': 'openai/gpt-4o', 'combined_model_name': 'openrouter/openai/gpt-4o', 'stripped_model_name': 'openai/gpt-4o', 'combined_stripped_model_name': 'openrouter/openai/gpt-4o', 'custom_llm_provider': 'openrouter'}
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:1131 -
litellm-1  |
litellm-1  | POST Request Sent from LiteLLM:
litellm-1  | curl -X POST \
litellm-1  | https://openrouter.ai/api/v1/chat/completions \
litellm-1  | -H 'HTTP-Referer: https://litellm.ai' -H 'X-Title: liteLLM' -H 'Authorization: Be****57' -H 'Content-Type: application/json' \
litellm-1  | -d '{'model': 'openai/gpt-4o', 'messages': [{'role': 'system', 'content': 'You are an LLM named MyModel'}, {'role': 'user', 'content': 'what is your name?'}], 'stream': False, 'usage': {'include': True}}'
litellm-1  |
litellm-1  |
litellm-1  | 11:33:21 - LiteLLM:DEBUG: litellm_logging.py:1204 - RAW RESPONSE:

/v1/responses

litellm-1  | 11:33:40 - LiteLLM:DEBUG: llm_http_handler.py:2238 - Creating HTTP client for responses API with shared_session: 140659107816384
litellm-1  | 11:33:40 - LiteLLM:DEBUG: litellm_logging.py:1131 -
litellm-1  |
litellm-1  | POST Request Sent from LiteLLM:
litellm-1  | curl -X POST \
litellm-1  | https://openrouter.ai/api/v1/responses \
litellm-1  | -H 'Authorization: Be****34' \
litellm-1  | -d '{'model': 'openrouter/openai/gpt-4o', 'input': [{'role': 'system', 'content': [{'type': 'input_text', 'text': 'You are an LLM named MyModel'}]}, {'content': 'what is your name?', 'role': 'user'}], 'store': False, 'temperature': 0.5}'
litellm-1  |
litellm-1  |

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.82.3

Twitter / LinkedIn details

No response

extent analysis

TL;DR

The /v1/responses endpoint does not correctly resolve the model alias, causing the request to fail with an invalid model ID error.

Guidance

The issue seems to be related to how the model alias is being resolved in the /v1/responses endpoint.
Compare the request payloads for /chat/completions and /v1/responses to identify any differences in how the model is specified.
Verify that the model_list configuration is being applied correctly to the /v1/responses endpoint.
Check if there are any endpoint-specific settings or overrides that might be causing the discrepancy.

Example

No code example is provided as the issue seems to be related to configuration or endpoint-specific behavior.

Notes

The issue might be specific to the v1.82.3 version of LiteLLM, and it's recommended to check the documentation or release notes for any known issues or updates related to model alias resolution.

Recommendation

Apply a workaround by ensuring that the model alias is correctly resolved in the /v1/responses endpoint, potentially by updating the configuration or modifying the request payload to match the expected format.

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?

#api #tokenizer error #prompt formatting #chain error #conversation history

Still need to ship something?

×6

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

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

litellm - 💡(How to fix) Fix [Bug]: response API wrong model name resolution [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

litellm - 💡(How to fix) Fix [Bug]: response API wrong model name resolution [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING