Skip to main content
The best model depends on your use case. You can browse the full list on the Supported AI Models page, or call the GET /v1/models endpoint to get the current list programmatically.As a starting point, gemini-2.5-flash offers a good balance of speed and quality for most tasks.
Response speed varies based on model size, task complexity, and server load. Smaller models (e.g., google/gemma-3-12b-it) tend to respond faster, while larger models (e.g., Qwen/Qwen3-235B-A22B-Instruct-2507) provide more capable responses. We recommend benchmarking with your specific use cases to find the best fit.
Call the GET /v1/models endpoint to get a real-time list of all available models:
curl https://gateway.iotex.ai/v1/models \
  -H "Authorization: Bearer your-api-key"
Yes. Since all models use the same OpenAI-compatible API format, switching models is as simple as changing the model parameter in your request. No other code changes are needed.