GreenPT Docs

Chat Completion Streaming

Stream chat completions with the GreenPT model for real-time responses.

POST

Stream chat completions with the GreenPT model for real-time responses.

Endpoint

POST https://api.greenpt.ai/v1/chat/completions

Request body

Required and optional parameters.

ParameterTypeRequiredDescription
modelstringYesID of the model to use (e.g., "green-l").
messagesarrayYesArray of message objects with role and content.
streambooleanYesMust be set to true for streaming responses.

Example request

curl https://api.greenpt.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your_api_key" \
  -d '{
    "model": "green-l",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "stream": true
  }'

Streaming response format

The response is a text stream of Server-Sent Events (SSE). Each event is a JSON object prefixed with data: , terminated by a final data: [DONE] sentinel.

data: {"id":"cmpl-12345","object":"chat.completion.chunk","created":1699044968,"model":"green-l","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]}

data: {"id":"cmpl-12345","object":"chat.completion.chunk","created":1699044968,"model":"green-l","choices":[{"index":0,"delta":{"content":"! How"},"finish_reason":null}]}

data: {"id":"cmpl-12345","object":"chat.completion.chunk","created":1699044968,"model":"green-l","choices":[{"index":0,"delta":{"content":" can I help you today?"},"finish_reason":null}]}

data: {"id":"cmpl-12345","object":"chat.completion.chunk","created":1699044968,"model":"green-l","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Reading the stream

Each chat.completion.chunk carries an incremental delta. Concatenate delta.content across chunks to assemble the full assistant message. The final non-[DONE] chunk includes a finish_reason ("stop", "length", etc.) and no further content.

Models

See the full list of available models on the Models page.

Chat Completion

Create a chat completion with the GreenPT model. We recommend gemma4.

Embeddings

Convert text into numerical vectors for semantic search and similarity matching.

On this page

EndpointRequest bodyExample requestStreaming response formatModels