Chat completions - Icelake API

Endpoint

POST /api/v1/chat/completions

OpenAI-compatible chat. Supports streaming and non-streaming responses.

Request body

Field	Type	Description
`model`	string	Model id from `GET /models`
`messages`	array	OpenAI-style message objects
`stream`	boolean	Default `false` for pure OpenAI clients; set `true` for SSE
`temperature`	number	Optional sampling
`top_p`	number	Optional nucleus sampling
`max_tokens`	integer	Optional max output tokens
`icelake_parameters`	object	Optional Icelake extensions

Example

curl https://icelake.io/api/v1/chat/completions \
  -H "Authorization: Bearer $ICELAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-2",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false,
    "max_tokens": 256
  }'

const res = await client.chat.completions.create({
  model: "zai-org-glm-5-2",
  messages: [{ role: "user", content: "Hello" }],
  stream: false,
  max_tokens: 256,
});

res = client.chat.completions.create(
    model="zai-org-glm-5-2",
    messages=[{"role": "user", "content": "Hello"}],
    stream=False,
    max_tokens=256,
)

Streaming

Set stream: true. Response is text/event-stream with OpenAI-style chunks, ending with:

data: [DONE]

Response headers

Header	Meaning
`x-request-id`	Support / debugging id
`x-icelake-model-id`	Resolved public model id
`x-icelake-balance-credits`	Wallet balance after reserve/charge
`x-ratelimit-limit-requests`	Configured RPM for the key

Billing

API key chat usage is metered in credits (not free daily chat quotas used by the web app).