Overview

Planck AI Gateway is the public entry point for AI requests. Use one base URL:

https://api.inquantum.ai

The gateway exposes explicit, supported routes instead of an unrestricted generic proxy. This keeps billing, logging, routing, provider-key handling, and safety features consistent across requests.

Supported Public Routes

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`, `GET /v1/videos/{job_id}`, `GET /v1/videos/{job_id}/content`
Audio transcription	`POST /v1/audio/transcriptions`
Audio translation	`POST /v1/audio/translations`
Text to speech	`POST /v1/audio/speech`
Files	`GET /v1/files`, `POST /v1/files`, `GET /v1/files/{file_id}`, `DELETE /v1/files/{file_id}`, `GET /v1/files/{file_id}/content`
OpenAI-compatible models	`GET /v1/models`, `GET /v1/models/{model_id}`
Anthropic Messages with raw HTTP	`POST /v1/messages`
Anthropic Messages with the Anthropic SDK	`POST /anthropic/v1/messages`
Other native Anthropic endpoints	`/anthropic/v1/*`
Gateway metadata	`GET /v1/gateway/status`, `GET /v1/gateway/providers`

Basic OpenAI-Compatible Request

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-mini",
  messages: [{ role: "user", content: "Say hello." }],
});

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{ "role": "user", "content": "Say hello." }]
  }'

BYOK Provider Keys

When you use your own provider key, Planck still needs a Planck API key for authentication. Send the provider key separately:

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "X-Provider-Key: $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{ "role": "user", "content": "Say hello." }]
  }'

You can also put the Planck key in Planck-Auth and keep the provider key in Authorization:

Planck-Auth: Bearer $PLANCK_API_KEY
Authorization: Bearer $OPENAI_API_KEY

Custom And Self-Hosted Targets

Custom targets are for OpenAI-compatible endpoints that you run or have approved for your organization. They are not a generic public proxy. Custom targets are:

BYOK-only
limited to supported operations such as chat, responses, and embeddings
configured per organization before production use
required to use https for external targets
blocked from private-network destinations outside local development

Send the target base URL with Planck-Target-URL:

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "X-Provider-Key: $CUSTOM_PROVIDER_KEY" \
  -H "Planck-Target-URL: https://llm.example.com" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-70b",
    "messages": [{ "role": "user", "content": "Hello from my model." }]
  }'

For local development, localhost-style targets can be enabled by the gateway operator. This is intended for local testing only.

Anthropic

For raw HTTP requests, use the mapped Anthropic route:

curl https://api.inquantum.ai/v1/messages \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-4.5-sonnet",
    "max_tokens": 256,
    "messages": [{ "role": "user", "content": "Say hello." }]
  }'

Anthropic Messages requires max_tokens; Planck does not add a default when it is omitted. For the Anthropic SDK, use the SDK-friendly base URL and provide your Planck API key through its api_key option:

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["PLANCK_API_KEY"],
    base_url="https://api.inquantum.ai/anthropic",
)

message = client.messages.create(
    model="claude-4.5-sonnet",
    max_tokens=256,
    messages=[{"role": "user", "content": "Say hello."}],
)

The SDK option is named api_key, but the value is your Planck API key. Use X-Provider-Key separately only when you want to supply an Anthropic BYOK key explicitly. Other Anthropic-native endpoints are available under:

https://api.inquantum.ai/anthropic/v1/*

See Reasoning and thinking to configure effort levels in either request format.

Get Started

Models & Inference

Reliability & Controls

Observability

Prompt Management

Integrations

Gateway Integration

Overview

Supported Public Routes

Basic OpenAI-Compatible Request

BYOK Provider Keys

Custom And Self-Hosted Targets

Anthropic

​Overview

​Supported Public Routes

​Basic OpenAI-Compatible Request

​BYOK Provider Keys

​Custom And Self-Hosted Targets

​Anthropic

Overview

Supported Public Routes

Basic OpenAI-Compatible Request

BYOK Provider Keys

Custom And Self-Hosted Targets

Anthropic