Models overview
Each vendor's series is described by use, recommended API and call examples. Each page lists a few representative models. The full list and prices are in the model square.
| Series | Good for | Recommended API | Docs |
|---|---|---|---|
| OpenAI GPT | Coding, reasoning, agents, image generation | Chat Completions / Responses | View |
| Anthropic Claude | Coding, long documents, agents | Claude Messages | View |
| Google Gemini | Multimodal, long context, images, speech | Native Gemini | View |
| xAI Grok | Chat, image and video generation | Chat Completions | View |
| DeepSeek, Kimi, GLM, Qwen, MiniMax, Doubao and others | Chinese conversation, coding, good value | Chat Completions | View |
Choosing by use
| What you want to do | Try first |
|---|---|
| Write code, change projects, run agents | claude-opus-5-5, claude-sonnet-5-5, gpt-6.1-sol, gemini-3.7-flash |
| Everyday Q&A, batch processing, cost control | claude-haiku-5-5, gpt-5.4-mini, gemini-3.5-flash-lite, deepseek-v4-flash |
| Complex reasoning, math | gpt-6-astra, claude-opus-5-5, gemini-3.1-pro-preview, deepseek-v4-pro |
| Generate and edit images | gpt-image-2.5, gemini-3-pro-image, grok-imagine-image-2.0 |
| Generate video | grok-imagine-video-1.5 |
| Text-to-speech, speech-to-text | gemini-3.8-flash-tts, gemini-3.5-transcribe |
| Semantic search, knowledge-base embeddings | text-embedding-3-large, gemini-embedding-001 |
Group prices
| Group | Price |
|---|---|
az_gpt | Pay 30% of official price |
claude | Pay 23% of official price |
codex_gpt | Pay 4.45% of official price |
deepseek | 100% of official price |
gemini | Pay 20% of official price |
gemini_image | Pay 30% of official price |
gemini_vertex | Pay 41.53% of official price |
glm | 100% of official price |
gpt | Pay 10% of official price |
gpt_image | Pay 10% of official price |
grok | Pay 10% of official price |
kimi | 100% of official price |
minimax | 100% of official price |
opencode | 100% of official price |
qwen | Pay 50% of official price |
volcengine | 100% of official price |
A token can only call models in its own group. See Tokens and groups.
