Models

Listing models

Model availability changes over time as providers are added or updated, so do not hardcode a model list in your application — call this endpoint (or check the Models catalog page) instead. The endpoint does not require authentication and mirrors the OpenAI /v1/models response shape.

Full catalog with pricing

GET /api/v1/models follows the OpenAI shape, so it only returns ids. When you need modality, vendor, context length, Credit pricing and service tiers per model — for example to render a model picker or a price table in your own product — call GET /api/public/models instead. It needs no authentication.

Prices are returned as micro-credits strings (Credits x 1,000,000) to avoid float rounding: divide by 1,000,000 for the Credit amount, and keep them as strings or BigInt in your code. unitType tells you what the price is per (per_million_tokens, per_image, per_second, per_request...). A browsable version of the same data is the Models page in the main site navigation.