Models

One set of compatible endpoints reaches 50+ models across the major international and domestic providers. The live catalog is below. The exact callable model ids come from the runtime response of GET /v1/models.

Live catalog

The tables below list display names so you can see the coverage. For the exact model string you pass to the API, use the runtime list.

International

Provider	Models
OpenAI	GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT Image 2
Anthropic	Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5
Google	Gemini 3.5 Pro, Gemini 3.1 Pro, Gemini 3.5 Flash
xAI	Grok

Domestic

Provider	Models
DeepSeek	DeepSeek V4 Pro, DeepSeek V4 Flash
Qwen (通义千问)	Qwen-Max, Qwen-Plus
GLM (智谱)	GLM-5.2
Moonshot Kimi	Kimi

TIP

The catalog changes as models are added or retired. The names above are display names, not API ids; the authoritative list and exact ids always come from GET /v1/models.

Pull the callable list at runtime

GET /v1/models returns the models your key can currently call, along with the exact id to pass in the model field:

bash

curl https://swato.ai/v1/models \
  -H "Authorization: Bearer $SWATO_API_KEY"

The response is the standard OpenAI list shape; each id is ready to use in a request:

json

{
  "object": "list",
  "data": [
    { "id": "<exact-model-id>", "object": "model" }
  ]
}

Any concrete model string shown next to a display name on this page is illustrative only. Always use the id returned by GET /v1/models.

Select a model

Put the id you got from GET /v1/models in the model field of the request body:

bash

curl https://swato.ai/v1/chat/completions \
  -H "Authorization: Bearer $SWATO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<see GET /v1/models for the exact id>",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The protocol surface depends on your key

Which protocol surface a model is reached through (OpenAI-compatible / Anthropic-compatible / Gemini native) depends on the group platform of the key you call with. The same endpoint auto-routes based on your key's group platform.

An OpenAI-platform key reaches /v1/chat/completions and /v1/responses.
An Anthropic-platform key reaches /v1/messages.
A Google-platform key reaches /v1beta/models/{model}:{action}.

See Authentication and Routing and fallback for details.

Models ​

Live catalog ​

International ​

Domestic ​

Pull the callable list at runtime ​

Select a model ​

The protocol surface depends on your key ​