Endpoints | Synux Docs

Synux exposes OpenAI-compatible routes under one base URL:

https://api.synux.ai/v1

Authentication

Send the API key as a Bearer token on every request:

Authorization: Bearer YOUR_SYNUX_API_KEY

Requests with a JSON body also need:

Content-Type: application/json

Routes

Method	Path	Purpose
`GET`	`/models`	List models available to the authenticated key
`POST`	`/chat/completions`	Generate a response from a conversation
`POST`	`/responses`	Use the Responses API with a compatible model
`POST`	`/embeddings`	Create vector embeddings from text or other supported input

The complete URL for Chat Completions, for example, is https://api.synux.ai/v1/chat/completions.

List models

curl "https://api.synux.ai/v1/models" \
  --header "Authorization: Bearer ${SYNUX_API_KEY}"

Use the returned id exactly as the model value in a generation or embedding request. Dashboard model availability and pricing can change as providers add, retire, or reprice models.

Chat Completions

The minimum useful body contains a model ID and a message list:

{
  "model": "your-model-id",
  "messages": [
    { "role": "user", "content": "Explain this in one paragraph." }
  ]
}

Set stream to true to receive incremental server-sent events. See Streaming responses.

Responses

The Responses endpoint accepts an input with a compatible model:

{
  "model": "your-model-id",
  "input": "Explain this in one paragraph."
}

Embeddings

The Embeddings endpoint accepts text input with an embedding-capable model:

{
  "model": "your-embedding-model-id",
  "input": "Text to embed"
}

Response headers

Synux returns X-Request-Id with each gateway response. Capture it in logs and include it when reporting an issue. Do not log authorization headers or request content just to retain the request ID.

Endpoint-specific fields and limits depend on the selected model. Use the model catalog as the source of truth for current capabilities and pricing.