Skip to Content
API CallText GenerationAPI support and explanation of UCloud extended fields

ModelVerse OpenAPI

This document lists the APIs supported by ModelVerse and explains the custom extension fields.

Supported Protocol Endpoints

Protocol/APIDescriptionExample Path
OpenAI Chat CompletionsText dialogue/streaming outputPOST /v1/chat/completions
OpenAI ResponsesMulti-part output and tool callPOST /v1/responses
OpenAI ImagesImage generation, editingPOST /v1/images/generations, /v1/images/edits
OpenAI AudioText-to-speechPOST /v1/audio/speech
Model Enumeration (OpenAI/Gemini)Returns a list of available modelsGET /v1/models, GET /v1beta/models
Anthropic MessagesClaude protocol dialoguePOST /v1/messages
Google GeminiContent generation in /v1beta/models/{model}:{action} stylePOST /v1beta/models/*
Asynchronous TasksVideo/long-duration task submission and queryPOST /v1/tasks/submit, GET /v1/tasks/status

Custom Extension Fields

On top of compatibility with the official OpenAI/Gemini protocols, we provide a few optional fields that are only recognized when using ModelVerse OpenAPI; you do not need to fill these when directly calling official OpenAI services.

FieldApplicable InterfaceDescriptionUsage
web_searchPOST /v1/chat/completionsControls whether to enable internet search capabilities and choose a search provider. Disabled by default. Supported vendor: tencent_sougo (Tencent Sogou, default), bocha (Bocha API), bing.Add at the root node of the request JSON:
json<br/>"web_search": {<br/> "enable": true,<br/> "vendor": "tencent_sougo"<br/>}
thinking_enabledPOST /v1/chat/completionsInternal “thinking mode” switch, affects model-side inference strategy. Disabled by default.Submit alongside the OpenAI request:
"thinking_enabled": true