Available Models
The platform aggregates mainstream models from multiple providers. The tables below are examples of commonly available models. For the exact model IDs, context lengths, and unit prices, refer to the console Models / Pricing page — they are adjusted along with upstream channels.
TIP
Use the GET /v1/models endpoint to fetch the list of models actually available to your token — this is the authoritative way to check whether a model is available.
Chat & text completion models
OpenAI series
| Model ID | Context | Vision | Function calling | Notes |
|---|---|---|---|---|
gpt-4o | 128K | ✅ | ✅ | Flagship multimodal, balances speed and quality |
gpt-4o-mini | 128K | ✅ | ✅ | Lightweight and fast, for high-frequency simple tasks |
o3 | 200K | ✅ | ✅ | Deep-reasoning flagship |
o4-mini | 200K | ✅ | ✅ | Reasoning model, cost-effective |
gpt-4.1 | 1M | ✅ | ✅ | Ultra-long context, strong coding |
Anthropic Claude series
| Model ID | Context | Vision | Function calling | Notes |
|---|---|---|---|---|
claude-opus-4 | 200K | ✅ | ✅ | Top-tier reasoning and writing |
claude-sonnet-4 | 200K | ✅ | ✅ | Balanced capability and speed, recommended default |
claude-haiku-3-5 | 200K | ✅ | ✅ | Very fast and light, for real-time interaction |
Google Gemini series
| Model ID | Context | Vision | Function calling | Notes |
|---|---|---|---|---|
gemini-2.5-pro | 1M | ✅ | ✅ | Ultra-long context, multimodal flagship |
gemini-2.5-flash | 1M | ✅ | ✅ | Great value, very fast |
DeepSeek series
| Model ID | Context | Vision | Function calling | Notes |
|---|---|---|---|---|
deepseek-v3 | 64K | — | ✅ | Strong all-round ability, optimized for Chinese |
deepseek-r1 | 64K | — | — | Deep reasoning with chain-of-thought output |
Qwen series
| Model ID | Context | Vision | Function calling | Notes |
|---|---|---|---|---|
qwen-max | 32K | — | ✅ | Alibaba Cloud flagship, best-in-class Chinese |
qwen-vl-max | 32K | ✅ | ✅ | Specialized vision understanding |
qwen-long | 1M | — | ✅ | Long-document processing |
Embedding models
| Model ID | Dimensions | Notes |
|---|---|---|
text-embedding-3-small | 1536 | General semantic search, cost-effective |
text-embedding-3-large | 3072 | High-precision semantic understanding |
text-embedding-ada-002 | 1536 | Compatibility with older projects |
Image generation models
| Model ID | Max resolution | Notes |
|---|---|---|
dall-e-3 | 1792×1024 | By OpenAI, stable quality |
gpt-image-1 | 1536×1024 | New-generation image model |
flux-1-pro | 2048×2048 | Open-source ecosystem, rich detail |
stable-diffusion-3 | 1024×1024 | Community ecosystem |
Audio models
| Model ID | Type | Notes |
|---|---|---|
tts-1 | TTS | Standard quality, low latency |
tts-1-hd | TTS | HD quality |
whisper-1 | STT | Multilingual recognition, 99 languages |
Video generation models
| Model ID | Max duration | Notes |
|---|---|---|
sora-2 | 20s | By OpenAI, high quality |
kling-v2 | 10s | Optimized prompts, natural motion |
wan-2.1 | 8s | Open-source video model |
Note on model updates
The platform continually onboards the latest models; the tables above are for reference only. The real-time data on the console Pricing / Models page is authoritative.