Streaming

Streaming returns tokens as the model generates them, reducing time-to-first-token. The stream format is identical to OpenAI and Anthropic.

OpenAI format

Set stream: true in your Chat Completions request.

curl -X POST https://api.radium.cloud/v1/chat/completions \\
  -H "Authorization: Bearer $RADIUM_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "clarke-1.0",
    "messages": [{"role": "user", "content": "Count to 5"}],
    "stream": true
  }'

from openai import OpenAI
client = OpenAI(api_key="YOUR_RADIUM_API_KEY", base_url="https://api.radium.cloud/v1")
stream = client.chat.completions.create(
    model="clarke-1.0",
    messages=[{"role": "user", "content": "Count to 5"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.RADIUM_API_KEY, baseURL: "https://api.radium.cloud/v1" });
const stream = await client.chat.completions.create({
  model: "clarke-1.0",
  messages: [{ role: "user", content: "Count to 5" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0].delta.content || "");
}

Anthropic format

Streaming works the same way in the Messages API. Set stream: true.

Limitations

Tool call streaming follows the same partial-delta format as OpenAI. Function arguments arrive as incremental JSON deltas in the tool_calls array. The final chunk contains the complete tool call with finish_reason: "tool_calls".