중국 본토 사용자 안내: 중국 본토 사용자는
https://toapis.cn 를 API 엔드포인트(Base URL)로 사용해 주세요. 본 문서의 예시에서 https://toapis.com 을 https://toapis.cn 로 바꿔 주세요.model parameter to switch models:
모델 marked as
응답s Only only support the 응답s API and do not support Chat Completions. Other models are called through Chat Completions by default.Anthropic / Claude
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
claude-haiku-4-5 | Fastest and most cost-effective Claude model, ideal for high-throughput lightweight tasks | ✓ | |
claude-sonnet-4-6 | Best balance of performance and cost, suitable for most business use cases | ✓ | |
claude-opus-4-6 | Claude 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.| 모델 ID | 설명 | Vision | Thinking | API Format |
|---|---|---|---|---|
gpt-5-pro-official | Official GPT-5 Pro, OpenAI’s strongest flagship reasoning model | ✓ | ✓ | 응답s Only |
gpt-5.2-official | Official GPT-5.2 with enhanced multimodal capabilities | ✓ | ✓ | All |
gpt-5.3-codex-official | Official GPT-5.3 Codex, latest code-optimized model with function calling and built-in tools | ✓ | ✓ | 응답s Only |
GPT-5 Standard
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
gpt-5 | OpenAI flagship model with powerful general reasoning and multimodal capabilities | ✓ | |
gpt-5-codex | GPT-5 optimized for code, excels at code generation and debugging | ||
gpt-5-codex-mini | Lightweight code model with ultra-fast response and low cost | ||
gpt-5.1 | GPT-5 enhanced, with improved instruction following and reasoning | ✓ | |
gpt-5.1-codex | GPT-5.1 code-specialized variant | ||
gpt-5.1-codex-max | GPT-5.1 flagship code model, maximum coding capability | ||
gpt-5.1-codex-mini | GPT-5.1 lightweight code variant, fast and cost-efficient | ||
gpt-5.2 | GPT-5 second generation with enhanced multimodal capabilities | ✓ | |
gpt-5.2-codex | GPT-5.2 code-specialized variant | ||
gpt-5.3-codex | Latest GPT-5 code model with continuously improving capabilities | ||
gpt-5.3-codex-spark | GPT-5.3 Codex Spark variant, focused on high-speed code generation | ||
gpt-5.4 | GPT-5 generation 4, enhanced general reasoning and multimodal capabilities | ✓ | |
gpt-5.5 | GPT-5.5 with enhanced general reasoning, coding, and multimodal capabilities | ✓ |
Google / Gemini
Gemini 3 Series
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
gemini-3.1-pro-preview-official | Gemini 3.1 Pro, latest flagship reasoning model | ✓ | ✓ |
gemini-3.1-flash-lite-preview-official | Gemini 3.1 Flash Lite, cost-effective lightweight model with fast responses | ✓ | |
gemini-3-pro-official | Gemini 3 Pro flagship with strong reasoning and multimodal capabilities | ✓ | ✓ |
gemini-3-pro-preview-official | Gemini 3 Pro Preview, same as gemini-3-pro-official | ✓ | ✓ |
gemini-3-flash-official | Gemini 3 Flash, fast and efficient | ✓ | ✓ |
gemini-3-flash-preview-official | Gemini 3 Flash Preview, same as gemini-3-flash-official | ✓ | ✓ |
gemini-3.1-fast | Google Gemini fast variant, high-value multimodal model | ✓ | |
gemini-3.1-thinking | Google Gemini thinking variant with built-in reasoning chain | ✓ | ✓ |
Gemini 2.5 Series
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
gemini-2.5-pro-official | Gemini 2.5 Pro with strong reasoning and long-context capabilities | ✓ | ✓ |
gemini-2.5-flash-official | Gemini 2.5 Flash, fast reasoning with thinking mode | ✓ | ✓ |
gemini-2.5-flash-lite-official | Gemini 2.5 Flash Lite, ultra-low-cost and fast lightweight model | ✓ |
Gemini 2.0 Series
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
gemini-2.0-flash-official | Gemini 2.0 Flash, classic fast model | ✓ | |
gemini-2.0-flash-lite-official | Gemini 2.0 Flash Lite, lowest-cost lightweight model | ✓ |
DeepSeek
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
deepseek-v3.2 | DeepSeek flagship model with extended thinking support, excels at code and complex reasoning | ✓ |
Alibaba / Qwen
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
qwen3-max | Qwen flagship model with deep thinking support, excels at complex reasoning and code generation | ✓ | |
qwen3.5-plus | Qwen enhanced model, balanced performance and cost | ||
qwen3.5-flash | Qwen ultra-fast model, ideal for low-latency and high-throughput scenarios |
Zhipu / GLM
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
glm-5 | Zhipu flagship model with outstanding Chinese language understanding and generation |
Moonshot / Kimi
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
kimi-k2.5 | Moonshot flagship model with ultra-long context and strong Chinese language capabilities |
MiniMax
| 모델 ID | 설명 | Vision | Thinking |
|---|---|---|---|
MiniMax-M2.5 | MiniMax flagship model with excellent cost-effectiveness |