Chat Completions
Primary endpoint for multi-turn chat, streaming, tool/function calling, and vision (model-dependent).
Endpoint: POST /v1/chat/completions
Request
curl https://api.starrise.ai/v1/chat/completions \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
}'Streaming
Set "stream": true. Response uses Server-Sent Events (SSE) with data: {...} chunks.
from openai import OpenAI
client = OpenAI(
base_url="https://api.starrise.ai/v1",
api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
)
stream = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")Legacy Completions
Endpoint: POST /v1/completions — OpenAI legacy prompt format.
Parameters
Supports standard OpenAI fields: model, messages, temperature, top_p, max_tokens, tools, tool_choice, response_format, stream, etc. Unsupported fields may be ignored or forwarded depending on upstream channel.
Related
- Responses API — OpenAI Responses format
- Claude Messages — Anthropic-native path
- Models — list available models