Text Model Support Matrix

The complexity of the text series lies not in “having many models,” but in “having many protocols.” The current system supports OpenAI Chat Completions, OpenAI Responses, Claude Messages, Gemini native format, Legacy Completions, and Realtime at the same time. Without a matrix, external users can easily see only the API name, without knowing which protocol they should integrate with.

This page is organized by “protocol style + capability type,” rather than listing models one by one. Which models are actually available to a single API key is still determined by the result returned from Model List.

Protocol Overview

Protocol/Capability	Recommended Entry	Typical Model Families	Streaming	Tool Calling	Multimodal	Use Cases
OpenAI Chat Completions	`/v1/chat/completions`	GPT, Claude mapped models, Gemini mapped models, DeepSeek, Qwen, etc.	Supported	Supported	Supported	Chat, Agent, legacy OpenAI SDK compatibility
OpenAI Responses	`/v1/responses`	GPT, compatibility models that support Responses semantics	Supported	Supported	Supported	Structured output, tool orchestration, context continuation
Claude Messages	`/v1/messages`	Claude Sonnet / Opus / Haiku, etc.	Supported	Supported	Supported	Existing Anthropic SDK or Claude native prompt structure
Gemini Native	`/v1beta/models/{model}:{action}`	Gemini Flash / Pro / image preview models	Supported	Supported	Supported	Existing Gemini SDK, preserving `contents/parts` structure
Legacy Completions	`/v1/completions`	Text models compatible with the legacy Completion style	Usually not preferred	Limited	No	Legacy system compatibility
Realtime	`/v1/realtime`	Real-time conversational models	Real-time streaming	Depends on model	Multimodal depends on the model	WebSocket real-time interaction

Common Model Name Examples

The following are not a “complete list of available models,” but examples of common text model names that are most likely to be encountered externally in the current system. Actual availability still depends on your channel configuration and the result returned by GET /v1/models.

OpenAI / GPT Style

Common Model Name	Description
`gpt-4o`	General-purpose multimodal model
`gpt-4o-mini`	Lightweight general-purpose model
`gpt-4.1`	General-purpose text/tool-calling model
`gpt-4.1-mini`	Lightweight 4.1
`gpt-4.1-nano`	Smaller 4.1 variant
`o1`	Reasoning model
`o3`	Reasoning model
`o4`	Reasoning model

Claude

Common Model Name	Description
`claude-sonnet-4-20250514`	Common version in the Claude Sonnet family
`claude-sonnet-4-5-20250929`	Later Sonnet version
`claude-sonnet-4-6`	Sonnet 4.6
`claude-opus-4-20250514`	Claude Opus family
`claude-opus-4-1-20250805`	Later Opus version
`claude-opus-4-6`	Opus 4.6
`claude-opus-4-7`	Opus 4.7
`claude-haiku-4-5-20251001`	Lightweight Haiku model

Gemini

Common Model Name	Description
`gemini-2.0-flash`	Gemini general fast model
`gemini-2.5-flash`	Gemini 2.5 Flash
`gemini-2.5-pro`	Gemini 2.5 Pro
`gemini-3.1-pro-preview`	Gemini preview Pro model
`gemini-3-pro-image-preview`	Gemini image preview model
`gemini-3.1-flash-image-preview`	Gemini image preview fast model

DeepSeek

Common Model Name	Description
`deepseek-chat`	General chat model
`deepseek-reasoner`	Reasoning model
`deepseek-v4-flash`	New-generation fast model
`deepseek-v4-pro`	New-generation advanced model
`deepseek-r1`	Reasoning series
`deepseek-r1-distill-qwen-32b`	Distilled reasoning model

Qwen

Common Model Name	Description
`qwen-max`	High-spec Qwen model
`qwen3-max`	High-spec model in the Qwen 3 family
`qwen3-omni-flash`	Qwen multimodal fast model
`qwq` / `qwq-*`	Common naming for the Qwen reasoning series

Choose an Entry Point by Protocol

1. OpenAI Chat Completions

Item	Description
Entry	`POST /v1/chat/completions`
Typical Fields	`model`, `messages`, `stream`, `tools`, `response_format`
Multimodal Input	`messages[].content` supports `text`, `image_url`, `input_audio`, `file`, `video_url`
Best For	Users already using the OpenAI SDK and wanting the lowest migration cost
Typical Model Families	GPT, Claude mapped models, Gemini mapped models, DeepSeek, Qwen
Common Model Name Examples	`gpt-4o`, `gpt-4.1`, `gpt-4o-mini`, `deepseek-chat`, `deepseek-reasoner`, `qwen-max`

2. OpenAI Responses

Item	Description
Entry	`POST /v1/responses`
Typical Fields	`model`, `input`, `instructions`, `tools`, `previous_response_id`, `text`
Advantages	Better suited for structured output, tool calling, and complex task orchestration
Streaming	Supports SSE
Typical Model Families	GPT-style models and upstream models compatible with Responses semantics
Common Model Name Examples	`gpt-4o`, `gpt-4.1`, `o1`, `o3`

3. Claude Messages

Item	Description
Entry	`POST /v1/messages`
Typical Fields	`model`, `messages`, `system`, `max_tokens`, `tools`, `thinking`
Auth Compatibility	`Authorization: Bearer` or `x-api-key` + `anthropic-version`
Best For	Users who already have Claude native-format calling code
Common Model Name Examples	`claude-sonnet-4-20250514`, `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-opus-4-7`

4. Gemini Native

Item	Description
Entry	`POST /v1beta/models/{model}:generateContent`
Typical Fields	`contents`, `generationConfig`, `tools`, `safetySettings`
Auth Compatibility	`Authorization: Bearer` or `x-goog-api-key`
Best For	Cases where you need to fully preserve the Gemini `contents/parts` structure, image parts, and Google tool style
Common Model Name Examples	`gemini-2.0-flash`, `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-3.1-pro-preview`

Choose an Interface by Capability

Conversation Generation

Need	Recommended Interface	Description
General chat	`/v1/chat/completions`	The most general-purpose and compatible
Tool orchestration	`/v1/responses`	Better suited for structured workflows
Claude native	`/v1/messages`	Preserve the Anthropic request structure
Gemini native	`/v1beta/models/{model}:generateContent`	Preserve the Gemini request structure

Realtime and Model Query

Need	Recommended Interface	Description
Real-time connection	`/v1/realtime`	WebSocket real-time session
Query available models for the current key	`/v1/models`	Returns the default OpenAI-style response
Query Gemini native models	`/v1beta/models`	Preserves the Gemini native model format

Common Model Family Mapping Approach

Family	Common Integration	Description
GPT / OpenAI-style models	`/v1/chat/completions` or `/v1/responses`	By default, prioritize OpenAI-compatible protocols
Claude	`/v1/messages` or `/v1/chat/completions`	For new integrations, `messages` is recommended; the compatibility layer can also use chat
Gemini	`/v1beta/models/{model}:{action}` or `/v1/chat/completions`	Use `v1beta` for native capabilities, or chat for unified SDK compatibility
DeepSeek / Qwen and other OpenAI-style upstream models	`/v1/chat/completions`	Usually the simplest option

Selection Recommendations

If you are already an OpenAI SDK client, start with the General Chat Interface (default streaming).
If you need tool calling, context continuation, or structured output, prefer the OpenAI Multimodal Responses Interface.
If you already have the Anthropic SDK, connect directly to the Claude Messages Interface.
If you already have the Gemini SDK or need to preserve the contents/parts structure, connect directly to the Gemini Native Format.
If you need low-latency bidirectional voice or a real-time session, check the Realtime Interface first.
If you are not sure which models your current key can use, check the Model List first.

Overview

Text Models

Image Models

Video Models

Uploads

Tasks

Account

Text Model Support Matrix

Text Model Support Matrix

Protocol Overview

Common Model Name Examples

OpenAI / GPT Style

Claude

Gemini

DeepSeek

Qwen

Choose an Entry Point by Protocol

1. OpenAI Chat Completions

2. OpenAI Responses

3. Claude Messages

4. Gemini Native

Choose an Interface by Capability

Conversation Generation

Realtime and Model Query

Common Model Family Mapping Approach

Selection Recommendations

​Text Model Support Matrix

​Protocol Overview

​Common Model Name Examples

​OpenAI / GPT Style

​Claude

​Gemini

​DeepSeek

​Qwen

​Choose an Entry Point by Protocol

​1. OpenAI Chat Completions

​2. OpenAI Responses

​3. Claude Messages

​4. Gemini Native

​Choose an Interface by Capability

​Conversation Generation

​Realtime and Model Query

​Common Model Family Mapping Approach

​Selection Recommendations

Text Model Support Matrix

Protocol Overview

Common Model Name Examples

OpenAI / GPT Style

Claude

Gemini

DeepSeek

Qwen

Choose an Entry Point by Protocol

1. OpenAI Chat Completions

2. OpenAI Responses

3. Claude Messages

4. Gemini Native

Choose an Interface by Capability

Conversation Generation

Realtime and Model Query

Common Model Family Mapping Approach

Selection Recommendations