Make your first request

Create a key, send a request, and check its cost. Already have a key? Start at step 2.

1. Create an API key

Sign in to the console. Follow onboarding, or open api keys → new in your workspace. Copy the key when it is shown and check that the workspace has credits. Set it in the terminal where you will run the example:

export IMPOSSIBL_API_KEY="your-impossibl-api-key"

Keep the key on your server or local machine, never in browser code. An agent can use API registration instead.

2. Send a request

Choose one tab. openai/gpt-4o-mini is a small text model used for this first call; you can replace it with another text model from the catalog.

cURL
Python
TypeScript

curl --fail-with-body https://api.impossibl.com/v1/chat/completions \
  -H "Authorization: Bearer $IMPOSSIBL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Write a one-sentence welcome for a notes app."}],
    "max_tokens": 128
  }'

The answer is in choices[0].message.content.

Example response

Text and token counts vary. This response is abbreviated:

{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "Welcome to your space for notes and ideas."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

Install the SDK:

python -m pip install openai

Save this as quickstart.py:

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Write a one-sentence welcome for a notes app."}],
    max_tokens=128,
)
print(response.choices[0].message.content)

Run it in the terminal where you exported the key:

python quickstart.py

Use Node.js 24 or later for this example and install the SDK:

npm install openai

Save this as quickstart.mts:

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Write a one-sentence welcome for a notes app." }],
  max_tokens: 128,
});
console.log(response.choices[0].message.content);

Run it in the terminal where you exported the key:

node quickstart.mts

3. Find your request

Open logs in the console. Select your request to see its status, tokens, latency, and cost. Make sure you are viewing the workspace that owns the API key.

Read the latest request through the API

You can also read the latest request through the API:

curl --fail-with-body "https://api.impossibl.com/v1/requests?limit=1" \
  -H "Authorization: Bearer $IMPOSSIBL_API_KEY"

If the request fails

Troubleshoot your first request

What you see	What to check
`401`	The environment variable contains an active impossibl key, and you are running in the terminal where you set it.
`402`	The key’s workspace has enough credits for the request. Add credits.
`403 billing_required`	The selected model requires purchased credits. Use the example model or make a credit purchase.
`404`	Use the full model ID from the live catalog, and keep `/v1` in the OpenAI SDK base URL.
`502` or `503`	Read the error message and troubleshoot the provider failure.

Next: stream the answer or connect your preferred SDK.

Get started

Build

Modalities

Manage

Make your first request

1. Create an API key

2. Send a request

3. Find your request

If the request fails

​1. Create an API key

​2. Send a request

​3. Find your request

​If the request fails

1. Create an API key

2. Send a request

3. Find your request

If the request fails