Skip to Content
API CallText GenerationModel protocol support description

Supported Protocols for Each Model

This page explains the compatibility of different models with various protocols.
Guidelines:

  • ✅: Currently recommended and verified primary invocation method.
  • Blank: Can be attempted but is not fully verified, potentially unstable, or completely unusable. It is recommended to validate in a test environment before use, as compatibility is not guaranteed.

Note: Actual compatibility may adjust with the evolution of official protocols. Please refer to the latest official documentation and test results.

How to View the List of Supported Models

You can obtain the list of supported models via the /v1/models interface:

curl https://api.umodelverse.ai/v1/models \
  -H "Content-Type: application/json"

It is recommended to use the Cherry Studio client. After configuring the API address, click the management button to visually view all supported models. For detailed configuration instructions, please refer to the Cherry Studio Configuration Tutorial.

OpenAI / GPT Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
gpt-5.1-chat✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
gpt-5.1✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
gpt-5.1-codex-mini✅Supports only /v1/responses interface
gpt-5.1-codex✅Supports only /v1/responses interface
gpt-5✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
gpt-5-chat✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
gpt-5-codex✅Supports only /v1/responses interface
gpt-4o-mini✅
gpt-4.1-nano✅
gpt-4.1-mini✅
o1✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-5.1-chat✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-5.1-codex✅Supports only /v1/responses interface
openai/gpt-5.1-codex-mini✅Supports only /v1/responses interface
openai/gpt-5.1✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-4o✅✅
openai/gpt-5-nano✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-4.1✅✅
openai/gpt-5✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-5-mini✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64
openai/gpt-oss-20b✅
openai/gpt-oss-120b✅
o4-mini-deep-research✅Supports only /v1/responses interface
o4-mini✅✅Does not support max_tokens parameter, use max_completion_tokens, for images use base64

Claude Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
claude-opus-4-1-20250805✅✅
claude-sonnet-4-5-20250929-thinking✅✅Only one of temperature or top_p can be specified, temperature range is [0,1)
claude-sonnet-4-5-20250929✅✅
claude-sonnet-3.7✅✅
claude-opus-4.1-thinking✅✅
claude-opus-4.0-thinking✅✅
claude-sonnet-4.0-thinking✅✅
claude-sonnet-3.5✅✅
claude-4-opus✅✅
claude-4-sonnet✅✅
claude-sonnet-4.5-thinking✅✅Only one of temperature or top_p can be specified, temperature range is [0,1)
claude-sonnet-4.5✅✅Only one of temperature or top_p can be specified, temperature range is [0,1)

Parameter Limitation Notice: Claude Sonnet 4.5 only supports specifying one of the temperature or top_p parameters, and not both simultaneously. See the official documentation description .

Grok Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
grok-4-1-fast-reasoning✅
grok-4-1-fast-non-reasoning✅
grok-4-fast-reasoning✅
grok-4-fast✅
grok-4✅

Qwen Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
Qwen/Qwen3-vl-Plus✅
Qwen/Qwen3-235B-A22B-Thinking-2507✅
Qwen/Qwen-Plus-Thinking✅
Qwen/Qwen-Plus✅
Qwen/Qwen3-Max✅
Qwen/Qwen3-VL-235B-A22B-Instruct✅
Qwen/Qwen3-VL-235B-A22B-Thinking✅
Qwen/Qwen3-32B✅
Qwen/Qwen3-30B-A3B✅
Qwen/Qwen3-Coder✅
Qwen/Qwen3-235B-A22B✅
Qwen/QwQ-32B✅
qwen/qwen2.5-vl-72b-instruct✅

Gemini Series (Supports /v1beta/models)

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
gemini-3-pro-preview✅Recommended to use /v1beta/models interface
gemini-2.5-pro✅Recommended to use /v1beta/models interface
gemini-2.5-flash✅Recommended to use /v1beta/models interface

Thinking Process Configuration: Using the Gemini protocol’s v1beta/models interface, you can enable/disable the thinking process through the thinkingConfig parameter. See Gemini Protocol Compatibility.

Safety Level Configuration: Gemini supports configuring content filtering strategies through safetySettings, covering categories like hate speech, pornography, dangerous content, harassment, and civic integrity. See the Google Official Safety Settings Document .

DeepSeek Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
deepseek-ai/DeepSeek-OCR✅
deepseek-ai/DeepSeek-V3.1-Think✅
deepseek-ai/DeepSeek-V3.2-Exp-Think✅
deepseek-ai/DeepSeek-V3.2-Exp✅
deepseek-ai/DeepSeek-V3.1-Terminus✅
deepseek-ai/DeepSeek-V3.1✅
deepseek-ai/DeepSeek-R1-Distill-Llama-70B✅
deepseek-ai/DeepSeek-R1-0528✅
deepseek-ai/DeepSeek-V3-0324✅
deepseek-ai/DeepSeek-R1✅

Doubao Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
ByteDance/doubao-1-5-pro-32k-250115✅
ByteDance/doubao-1-5-pro-256k-250115✅
ByteDance/doubao-seed-1.6✅
ByteDance/doubao-seed-1.6-thinking✅
ByteDance/doubao-1.5-thinking-vision-pro✅

Baidu Series

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
baidu/ernie-x1-turbo-32k✅
baidu/ernie-4.5-turbo-128k✅
baidu/ernie-4.5-turbo-vl-32k✅

Other Models

Model IDOpenAI Chat Protocol /v1/chat/completionsOpenAI Response Protocol /v1/responsesGemini Protocol /v1beta/modelsAnthropic Protocol /v1/messagesNotes
moonshotai/Kimi-K2-Thinking✅
moonshotai/Kimi-K2-Instruct-0905✅
moonshotai/Kimi-K2-Instruct✅
zai-org/glm-4.6✅
zai-org/glm-4.5v✅
zai-org/glm-4.5✅
kat-coder-256k✅
How to get the model listAPI support and explanation of UCloud extended fields