Skip to main content
The model, token group, and protocol used with NexusAPI must all match. Use the Model Marketplace and the result returned by your current key as the live source of truth.
Confirm before you call
  1. Confirm that the model is in your key’s token group in the Model Marketplace.
  2. Confirm that supported_endpoint_types returned by /v1/models includes the protocol you need.
  3. Use /v1/models to see what the key can actually access, then send a minimal request.

​
Publicly documented capabilities

Use the documented public capability scopeUse the capabilities listed on this page, in the Model Marketplace, or in an official guide. Image edits and variations, embeddings, audio, rerank, and native Gemini are not currently documented as general public NexusAPI capabilities; contact support before using any of them in production.

​
Check models with the current key

Copy a model ID from data[].id. data[].supported_endpoint_types lists the request protocols available for that model: openai for Chat Completions, anthropic for Messages, openai-response for Responses, and image-generation for image generation. A model can list more than one type; choose from that field for your client rather than guessing from a model name. /v1/models is a point-in-time view for one key. The Model Marketplace shows prices, groups, and descriptions. If they differ, follow the current key result and console state.

​
A simple protocol rule

If a model is visible but the call still fails, check its ID, your token group, and the request path first. Keep the Request ID and use the self-check guide.

​
Where to find details

Model availability and supported capabilities change. Ask support before using a capability not listed here.