Quickstart

Send a request through Planck’s OpenAI-compatible AI Gateway, then inspect its cost, latency, provider, input, and output in the dashboard.

Create a Planck API key

Create a Planck account or sign in.
Open API Keys and create a key.
Add credits or connect a provider key before making a model request.

Store the key in an environment variable. Do not commit it to source control.

export PLANCK_API_KEY="your-planck-api-key"

Install a client

Choose the language you want to use. cURL does not require an SDK.

TypeScript
Python
cURL

npm install openai

pip install openai

Confirm that cURL is available:

curl --version

Send a request

The only Planck-specific client settings are the gateway base URL and your Planck API key.

TypeScript
Python
cURL

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: "Explain gravity in one sentence." }],
});

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

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inquantum.ai/v1",
    api_key=os.environ["PLANCK_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Explain gravity in one sentence."}
    ],
)

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

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": "Explain gravity in one sentence."}
    ]
  }'

A successful response contains the generated text in choices[0].message.content.

Inspect the request

Open Requests. The request should appear within seconds with its model, provider, latency, token usage, cost, input, and output.If the request fails, use the returned status and error code with the error handling guide. The most common setup issues are a missing API key, no available credits or provider key, and an unsupported model name.

What just happened?

Your application sent an OpenAI-compatible request to Planck. Planck selected an eligible provider endpoint, returned a compatible response, and recorded the request for observability. To use the Anthropic SDK or keep model traffic on its existing path, see Choose an Integration.

Next steps

Explore every feature

Find gateway, reliability, observability, prompt, and integration features.

Choose a model

Discover supported operations, parameters, and provider endpoints.

Stream a response

Render generation as it arrives and handle streaming errors safely.

Add application context

Attach metadata that makes production requests easier to filter and debug.

Questions?

Contact help@inquantum.ai.

Get Started

Models & Inference

Reliability & Controls

Observability

Prompt Management

Integrations

What just happened?

Next steps

Explore every feature

Choose a model

Stream a response

Add application context

Questions?

​What just happened?

​Next steps

Explore every feature

Choose a model

Stream a response

Add application context

​Questions?

What just happened?

Next steps

Questions?