Streaming

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PRISM_API_KEY,
  baseURL: "https://api.prisminference.com/v1",
});

const stream = await client.chat.completions.create({
  model: "prism-glm53",
  messages: [{ role: "user", content: "Review this TypeScript diff: ..." }],
  stream: true,
  stream_options: { include_usage: true },
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content;
  if (delta != null) {
    process.stdout.write(delta);
  }

  if (chunk.usage != null) {
    console.error(`\n${chunk.usage.total_tokens} tokens`);
  }
}

curl -N "https://api.prisminference.com/v1/chat/completions" \
  -H "Authorization: Bearer $PRISM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "prism-glm53",
    "messages": [{"role": "user", "content": "Explain this diff: ..."}],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.PRISM_API_KEY,
  baseURL: "https://api.prisminference.com",
});

const stream = client.messages.stream({
  model: "prism-glm53",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain this diff: ..." }],
});

stream.on("text", (text) => {
  process.stdout.write(text);
});

const message = await stream.finalMessage();
console.error(`\n${message.usage.output_tokens} output tokens`);