← All docs

Model selection and access

1. Find models available to your key

GET /v1/models applies the key's allowed-model list and account or organization policies. The public model directory also displays models that need consent, so its list can differ from your key's list. Use the exact id returned by the API.

2. Check capabilities

FieldPurpose
categoryLLM / IMAGE / VIDEO
supported_endpointsPublic paths associated with the model
capabilities.streaming · tool_use · vision · json_modeStreaming, tools, image inputs, and JSON output requests
capabilities.web_searchServer-side web search through Chat
capabilities.json_mode_with_tools · web_search_with_toolsSupport for JSON+tools and web search+function tools
capabilities.sampling · structured_outputs · parallel_tool_calls · image_maskSampling, strict schemas, parallel-call control, and mask support
limits.reasoning_efforts · supported_sizes · supported_qualities · supported_durations · max_imagesModel-specific values and counts. Omitted fields mean unverified support
limits.max_tokens · context_windowModel-specific output and context limits
availableCurrent catalog availability

Model-specific parameter limits may be lower than the gateway's common limits. Messages and Responses use chat compatibility translation; they do not expose every upstream feature.

3. Check access policies

Community supply (supply) and provider training use (training_use) require separate consent, both off by default. Personal keys use account settings; organization keys use organization settings.

Required consentNo callable candidate in Chat, Messages, or Responses
Community-only model404 model_not_found
Training-only model404 model_not_found

mixed models use only permitted endpoints. If a model is missing, check the key's allowed models, both consent settings, and the model's active status.

4. Routing hints

Chat requests accept provider: {"sort": "latency", "allow_fallbacks": true}. sort accepts price, latency, or throughput; allow_fallbacks controls retries across supply routes. The former provider-name selectors only, order, and ignore have been retired and are ignored.

The models array accepts up to 5 fallback model IDs. Fallback happens only before credit reservation when the selected model is unavailable. It does not continue a failed generation using another model.

Catalog prices are reference costs; billing applies account rates. See model and pricing fields.