Documentation

Everything you need to integrate PrismAI into your applications.

Quick Start

Get up and running with PrismAI in under 5 minutes. PrismAI is fully compatible with the OpenAI SDK — just change the base URL.

1. Get your API key

2. Make your first request (cURL)

curl https://api.prismai.dev/llm/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

3. Or use the OpenAI SDK (TypeScript)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.prismai.dev/llm/v1",
  apiKey: process.env.PRISMAI_API_KEY,
});

const res = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "Hello!" }],
});

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

4. Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.prismai.dev/llm/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Authentication

All API requests require a valid API key passed in the Authorization header.

Authorization: Bearer sk-prismai-...

Create API keys in Dashboard → API Keys. Each key is shown only once upon creation.

Revoke compromised keys immediately from the dashboard. Revoked keys return 401.

API keys are hashed with SHA-256. We never store plaintext keys.

API Reference

PrismAI provides an OpenAI-compatible API. Use the same request format as OpenAI, plus native Anthropic passthrough.

POST/llm/v1/chat/completions

Create a chat completion. Supports all OpenAI-compatible parameters including streaming.

Parameters

modelRequired. The model ID (e.g. gpt-4o, claude-sonnet-4-6, gemini-2.5-pro).

messagesRequired. Array of message objects with role and content.

streamOptional. Set to true for streaming responses via SSE.

temperatureOptional. Sampling temperature between 0 and 2.

POST/llm/anthropic/v1/messages

Native Anthropic Messages API passthrough. Use the exact same format as the Anthropic API.

GET/llm/v1/models

List all available models with pricing, context window, and capability information.

Supported Models

PrismAI supports 100+ models across major providers. Here are the most popular ones:

OpenAI

gpt-4o, gpt-4o-mini, o1, o3

Anthropic

claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5

Google

gemini-2.5-pro, gemini-2.5-flash

DeepSeek

deepseek-chat, deepseek-reasoner

Credits & Billing

PrismAI uses a credit-based billing system. Credits are consumed based on the upstream cost of each API call.

Credits are managed at the organization level. All members share the org balance.
Each API call deducts credits based on actual token usage and model pricing.
Credits never expire. Purchase once, use anytime.
Top up credits from Dashboard → Settings → Billing.

Rate Limits

Rate limits are applied per API key to ensure fair usage.

Tier	Requests / min	Tokens / min
Free	10	40,000
Starter	60	200,000
Pro	300	1,000,000