Quickstart

Prism accepts OpenAI Chat Completions requests at https://api.prisminference.com/v1. You need a Prism API key and a public model ID.

Send your first request

Set your API key

export PRISM_API_KEY="YOUR_PRISM_API_KEY"

Store the key in your server-side secret manager. Do not commit it or expose it to browser code.

Call a model

curl --fail-with-body "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": "Write a TypeScript function that limits concurrent promises."
      }
    ]
  }'

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "prism-glm53",
  messages: [
    {
      role: "user",
      content: "Write a TypeScript function that limits concurrent promises.",
    },
  ],
});

console.log(response.choices[0].message.content);

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PRISM_API_KEY"],
    base_url="https://api.prisminference.com/v1",
)

response = client.chat.completions.create(
    model="prism-glm53",
    messages=[
        {
            "role": "user",
            "content": "Write a TypeScript function that limits concurrent promises.",
        }
    ],
)

print(response.choices[0].message.content)

Install the OpenAI client with npm install openai or pip install openai.

Read the completion

The endpoint returns a standard Chat Completions response:

{
  "id": "chatcmpl_01J...",
  "object": "chat.completion",
  "created": 1788926400,
  "model": "prism-glm53",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is a concurrency limiter..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 142,
    "total_tokens": 160
  }
}

Assistant text is in choices[0].message.content. Token counts are in usage.

Stream tokens

Pass stream: true to receive incremental Chat Completions chunks:

const stream = await client.chat.completions.create({
  model: "prism-glm53",
  messages: [{ role: "user", content: "Explain optimistic locking." }],
  stream: true,
});

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

Use the Anthropic format

Prism also accepts Anthropic Messages requests. Point an Anthropic client at https://api.prisminference.com without the /v1 suffix:

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

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

const message = await client.messages.create({
  model: "prism-glm53",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Write a tiny rate limiter in TypeScript." }],
});

Next steps

Choose a model

Compare the public model IDs and context windows.

Stream responses

Handle chunks, usage, disconnects, and retries.

Call tools

Run the OpenAI or Anthropic tool-use loop.

Return JSON

Constrain model output to valid JSON or a schema.

Get started

API reference

Guides

Resources

Send your first request

Stream tokens

Use the Anthropic format

Next steps

Choose a model

Stream responses

Call tools

Return JSON

​Send your first request

​Stream tokens

​Use the Anthropic format

​Next steps

Choose a model

Stream responses

Call tools

Return JSON

Send your first request

Stream tokens

Use the Anthropic format

Next steps