Docs · Integrate

Models & selection

GET /v1/models lists the models available to your key. Prices, context length and capabilities are in the model catalog.

curl https://<your-endpoint>/v1/models \
  -H "Authorization: Bearer $API_KEY"

{
  "object": "list",
  "data": [
    { "id": "gpt-4.1-mini", "object": "model", "owned_by": "..." },
    { "id": "claude-sonnet-4-5", "object": "model", "owned_by": "..." }
  ]
}

The catalog today

151
models: 11
vendors: 3
model types

OpenAI44 Google20 Mistral AI18 Anthropic15 Alibaba15 Zhipu AI14 DeepSeek7 xAI6 MiniMax6 Moonshot AI4 ByteDance2

Choosing a model

Use case	Suggestion
General chat, support, summaries	A vendor's main model or its light tier (mini / flash / lite …)
Hard reasoning, coding, agents	Flagship and reasoning models (with the Reasoning and Tool calling capabilities)
High volume, cost-sensitive	Small models (mini, nano, flash, lite, turbo …) plus prompt caching
Long documents	Check the context length; some models use tiered pricing for long inputs
Image understanding	Models with the Vision capability
Image generation / retrieval	Models of type Image / Embedding

Model IDs must match the catalog exactly (case-sensitive). To switch models, change the model field.
Before launch, compare 2–3 candidates on your own samples — quality, latency and cost per request.
Every model page has a price breakdown and a cost estimate — see the model catalog.

Embeddings

Tool calling