OpenAI-compatible API

One API for every model that is live.

Use familiar OpenAI SDKs, discover the verified model catalog at runtime, and stream responses through one endpoint.

612 live models 4 providers OpenAI SDK compatible

Base URL https://ai.developpeurcasablanca.com/v1

Authentication

Send your developer key as a Bearer token with every request.

Keep keys on your server

Never expose a developer key in browser JavaScript, a mobile bundle or a public repository.

HTTP header

Authorization: Bearer dk_your_key_here

Quickstart

Replace the placeholder key and model with values from your account.

cURL · shell

curl https://ai.developpeurcasablanca.com/v1/chat/completions \
  -H "Authorization: Bearer dk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(
    api_key="dk_your_key_here",
    base_url="https://ai.developpeurcasablanca.com/v1",
)
reply = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Do not hard-code a guessed model name: call GET /v1/models and use an ID returned for your key.

`GET /v1/models`

Returns only enabled models currently available to the provider keys behind the service.

cURL · shell

curl https://ai.developpeurcasablanca.com/v1/models \
  -H "Authorization: Bearer dk_your_key_here"

JSON · response200 OK

{
  "object": "list",
  "data": [{
    "id": "model-id",
    "object": "model"
  }]
}

`POST /v1/chat/completions`

Create a response with the same request shape used by OpenAI chat completions.

modelRequired

A model ID returned by /v1/models.

messagesRequired

An ordered list of role and content objects.

streamOptional

Set true to receive incremental server-sent events.

Streaming

Set stream to true to start receiving tokens as soon as they are generated.

Python · streaming

stream = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Errors

Errors use standard HTTP status codes and a JSON error message.

Status	Meaning	What to do
`400`	Invalid request	Check the JSON fields and model ID.
`401`	Missing or invalid key	Create or replace your developer key.
`402`	Insufficient credit	Add prepaid API credit in your account.
`429`	Too many requests	Retry with exponential backoff.
`5xx`	Temporary service problem	Retry safely after a short delay.

Ready to make your first call?

Create an account, issue a developer key, then discover the live models available to it.

Get an API key