ToAPIsToAPIs

Supported Text モデル

Text model list supporting both Chat Completions and レスポンスs API formats

中国本土のユーザー向け: 中国本土のユーザーは https://toapis.cn を API エンドポイント(Base URL)としてご利用ください。本ドキュメント内の例では https://toapis.com を https://toapis.cn に置き換えてください。

The platform provides two API formats. Use the model parameter to switch models:

API Formatエンドポイント説明
Chat Completions (default)POST /v1/chat/completionsClassic chat API, compatible with OpenAI SDKs. View docs
レスポンスs (new)POST /v1/responsesNewer OpenAI agentic API with function calling, built-in tools, and server-side multi-turn context. View docs

モデル marked as レスポンスs Only only support the レスポンスs API and do not support Chat Completions. Other models are called through Chat Completions by default.


Anthropic / Claude

モデル ID説明VisionThinking
claude-haiku-4-5Fastest and most cost-effective Claude model, ideal for high-throughput lightweight tasks✓
claude-sonnet-4-6Best balance of performance and cost, suitable for most business use cases✓
claude-opus-4-6Claude flagship model, ideal for complex reasoning and high-quality generation✓

OpenAI / GPT-5

GPT-5 Official

Direct access through the official Azure OpenAI API, with the highest stability and compliance.

モデル ID説明VisionThinkingAPI Format
gpt-5-pro-officialOfficial GPT-5 Pro, OpenAI's strongest flagship reasoning model✓✓レスポンスs Only
gpt-5.2-officialOfficial GPT-5.2 with enhanced multimodal capabilities✓✓All
gpt-5.3-codex-officialOfficial GPT-5.3 Codex, latest code-optimized model with function calling and built-in tools✓✓レスポンスs Only

GPT-5 Standard

モデル ID説明VisionThinking
gpt-5OpenAI flagship model with powerful general reasoning and multimodal capabilities✓
gpt-5-codexGPT-5 optimized for code, excels at code generation and debugging
gpt-5-codex-miniLightweight code model with ultra-fast response and low cost
gpt-5.1GPT-5 enhanced, with improved instruction following and reasoning✓
gpt-5.1-codexGPT-5.1 code-specialized variant
gpt-5.1-codex-maxGPT-5.1 flagship code model, maximum coding capability
gpt-5.1-codex-miniGPT-5.1 lightweight code variant, fast and cost-efficient
gpt-5.2GPT-5 second generation with enhanced multimodal capabilities✓
gpt-5.2-codexGPT-5.2 code-specialized variant
gpt-5.3-codexLatest GPT-5 code model with continuously improving capabilities
gpt-5.3-codex-sparkGPT-5.3 Codex Spark variant, focused on high-speed code generation
gpt-5.4GPT-5 generation 4, enhanced general reasoning and multimodal capabilities✓
gpt-5.5GPT-5.5 with enhanced general reasoning, coding, and multimodal capabilities✓

Google / Gemini

Gemini 3 Series

モデル ID説明VisionThinking
gemini-3.1-pro-preview-officialGemini 3.1 Pro, latest flagship reasoning model✓✓
gemini-3.1-flash-lite-preview-officialGemini 3.1 Flash Lite, cost-effective lightweight model with fast responses✓
gemini-3-pro-officialGemini 3 Pro flagship with strong reasoning and multimodal capabilities✓✓
gemini-3-pro-preview-officialGemini 3 Pro Preview✓✓
gemini-3-flash-officialGemini 3 Flash, fast and efficient✓✓
gemini-3-flash-preview-officialGemini 3 Flash Preview✓✓
gemini-3.1-fastGoogle Gemini fast variant, high-value multimodal model✓
gemini-3.1-thinkingGoogle Gemini thinking variant with built-in reasoning chain✓✓

Gemini 2.5 Series

モデル ID説明VisionThinking
gemini-2.5-pro-officialGemini 2.5 Pro with strong reasoning and long-context capabilities✓✓
gemini-2.5-flash-officialGemini 2.5 Flash, fast reasoning with thinking mode✓✓
gemini-2.5-flash-lite-officialGemini 2.5 Flash Lite, ultra-low-cost and fast lightweight model✓

Gemini 2.0 Series

モデル ID説明VisionThinking
gemini-2.0-flash-officialGemini 2.0 Flash, classic fast model✓
gemini-2.0-flash-lite-officialGemini 2.0 Flash Lite, lowest-cost lightweight model✓

DeepSeek

モデル ID説明VisionThinking
deepseek-v3.2DeepSeek flagship model with extended thinking support, excels at code and complex reasoning✓

Alibaba / Qwen

モデル ID説明VisionThinking
qwen3-maxQwen flagship model with deep thinking support, excels at complex reasoning and code generation✓
qwen3.5-plusQwen enhanced model, balanced performance and cost
qwen3.5-flashQwen ultra-fast model, ideal for low-latency and high-throughput scenarios

Zhipu / GLM

モデル ID説明VisionThinking
glm-5Zhipu flagship model with outstanding Chinese language understanding and generation

Moonshot / Kimi

モデル ID説明VisionThinking
kimi-k2.5Moonshot flagship model with ultra-long context and strong Chinese language capabilities

MiniMax

モデル ID説明VisionThinking
MiniMax-M2.5MiniMax flagship model with excellent cost-effectiveness

On this page