AI Gateway Overview

Planck AI Gateway provides a unified API for supported LLM providers through OpenAI-compatible and Anthropic-compatible routes. Instead of wiring every provider directly into your application, use one familiar gateway interface with intelligent routing, fallbacks, billing, and complete observability built in.

Why Use AI Gateway?

One SDK for All Models

Use OpenAI SDK patterns to access GPT, Claude, Gemini, and other supported models

Unified Provider Access

Use managed access or your own configured provider keys from one API

Built-in Failover

Retry eligible failures across compatible provider endpoints

Unified Observability

Track usage, costs, and performance across all providers in one dashboard

How It Works

The AI Gateway sits between your application and LLM providers, acting as a unified translation layer:

You make one request - Use the OpenAI SDK format, regardless of which provider you want
We translate & route - Planck converts your request to the correct provider format (Anthropic, Google, etc.)
Provider responds - The LLM provider processes your request
We log & return - You get the response back while we capture metrics, costs, and errors

OpenAI-compatible SDKs use https://api.inquantum.ai/v1; Anthropic SDKs use https://api.inquantum.ai/anthropic.

Supported Gateway Surface

The current gateway uses explicit public routes instead of an unrestricted generic proxy.

Capability	Route
Chat completions	`POST /v1/chat/completions`
Structured JSON	`POST /v1/chat/completions` with `response_format`
Responses API	`POST /v1/responses`
Embeddings	`POST /v1/embeddings`
Reranking	`POST /v1/rerank`
Image generation	`POST /v1/images/generations`
Video generation	`POST /v1/videos`, then poll `GET /v1/videos/{job_id}`
Audio	`POST /v1/audio/transcriptions`, `POST /v1/audio/translations`, `POST /v1/audio/speech`
Files	`/v1/files*`
Anthropic messages (raw HTTP)	`POST /v1/messages`
Anthropic SDK messages	`POST /anthropic/v1/messages`
Other native Anthropic paths	`/anthropic/v1/*`
Models	`GET /v1/models`, `GET /v1/models/{model_id}`

With credits, we manage provider API keys for you. With BYOK, you provide your own provider keys while keeping Planck logging, routing, and observability.

Choose an Operation

Chat & Responses

Generate text with OpenAI-compatible or Anthropic-compatible request formats

Reasoning & Thinking

Configure normalized reasoning controls with OpenAI or Anthropic request shapes

Streaming

Render chat completions incrementally and handle SSE events safely

Tool Calling

Let models request safe, application-defined functions

Model Capabilities

Discover supported operations and parameters for each provider endpoint

Structured JSON

Constrain model output to a JSON Schema your application can validate

Embeddings

Convert text into vectors for search, retrieval, and similarity

Reranking

Reorder documents by relevance to a query

Image Generation

Generate an image through one gateway endpoint

Video Generation

Submit, monitor, and download asynchronous video generations

Quick Example

Add two lines to your existing OpenAI code to use the gateway with automatic observability:

import { OpenAI } from "openai";

const client = new OpenAI({
  baseURL: "https://api.inquantum.ai/v1", 
  apiKey: process.env.PLANCK_API_KEY, 
});

const response = await client.chat.completions.create({
  model: "gpt-4o", // Or another supported model
  messages: [{ role: "user", content: "Hello!" }],
});

Next Steps

Get Started in 5 Minutes

Set up AI Gateway and make your first request

Browse Model Registry

See available models and their supported capabilities

Provider Routing

Configure automatic routing and fallbacks for reliability

Prompt Integration

Deploy and manage prompts through the gateway

Get Started

Models & Inference

Reliability & Controls

Observability

Prompt Management

Integrations

AI Gateway Overview

Why Use AI Gateway?

One SDK for All Models

Unified Provider Access

Built-in Failover

Unified Observability

How It Works

Supported Gateway Surface

Choose an Operation

Chat & Responses

Reasoning & Thinking

Streaming

Tool Calling

Model Capabilities

Structured JSON

Embeddings

Reranking

Image Generation

Video Generation

Quick Example

Next Steps

Get Started in 5 Minutes

Browse Model Registry

Provider Routing

Prompt Integration

​Why Use AI Gateway?

One SDK for All Models

Unified Provider Access

Built-in Failover

Unified Observability

​How It Works

​Supported Gateway Surface

​Choose an Operation

Chat & Responses

Reasoning & Thinking

Streaming

Tool Calling

Model Capabilities

Structured JSON

Embeddings

Reranking

Image Generation

Video Generation

​Quick Example

​Next Steps

Get Started in 5 Minutes

Browse Model Registry

Provider Routing

Prompt Integration

Why Use AI Gateway?

How It Works

Supported Gateway Surface

Choose an Operation

Quick Example

Next Steps