Models

OpenUI Gateway supports hundreds of models from OpenAI, Anthropic, Google, Meta, Mistral, and other model labs.

Pass the model ID directly to the model field in either the Chat Completions or Responses API:

const response = await gateway.chat.completions.create({
  model: "openai/gpt-5.6-sol",
  messages,
});

Supported models

View supported models on Models.dev and copy the value from the Model ID column. Model IDs normally follow an {author}/{model-slug} format, such as openai/gpt-5.6-sol.

Use the complete ID. Do not pass only the model name:

model: "openai/gpt-5.6-sol" // Correct
model: "gpt-5.6-sol"        // Missing the author

Availability and capabilities

Input and output modalities, context length, tool support, and supported parameters vary by model. Check the model details on Models.dev before selecting a model.

For Generative UI, choose a model that produces text and follows structured output instructions reliably. Use the OpenUI model benchmarks as a guide when comparing models, alongside the latency, cost, context length, and capabilities required by your application. Gateway can validate and correct eligible OpenUI Lang errors, but the selected model still determines the quality and latency of the generated interface. See Reliability for details.

Add your own provider credentials with BYOK. For managed model usage and Gateway credits, see Pricing.