Model Overview
4ALL API aggregates 200+ models and uses a unified OpenAI-compatible interface; switching models only requires changing the model field.
For the complete real-time list and pricing, please refer to the console Model Hub.
Major Model Families
| Series | Representative Models | Best For |
|---|---|---|
| GPT | gpt-5.5, gpt-5.6-luna / -sol / -terra | General chat, coding, tool calling |
| GPT Lite/Code | gpt-5.4-mini, gpt-5.3-codex | Low-cost batch jobs, code generation |
| Claude | claude-sonnet-5, claude-opus-4-6, claude-haiku-4-5 | Long-form writing, complex reasoning, code |
| Gemini | gemini-3.5-flash, gemini-3.1-pro, gemini-3-flash | Multimodal understanding, high cost performance |
| Free Models | qwen/qwen3.6-plus:free, z-ai/glm-4.5-air:free, minimax/minimax-m2.5:free etc. | Trials and lightweight tasks (free group) |
Some models provide tier suffixes: -high / -low (reasoning strength), -thinking (thinking mode),
-google-search (web search, Gemini series).
For image and video models, see Image and Video Generation Models.
Get the Model List
curl https://api.4allapi.com/v1/models \ -H "Authorization: Bearer $AIPROXY_KEY"Returns the list of models available to the current token group.
Selection Recommendations
- General scenarios: prefer
gpt-5.5orclaude-sonnet-5; - Cost-sensitive batch tasks:
gpt-5.4-mini,gemini-3.5-flash,claude-haiku-4-5; - Complex reasoning:
claude-opus-4-6-thinking,gpt-5.5-high,gemini-3.1-pro-high; - Real-time web-augmented Q&A:
gemini-3.5-flash-google-search; - Zero-cost trial: free models in the
freegroup; - It is recommended to make the model name a configuration option in your business, so it is easier to do gray releases and compare the performance and cost of different models.