API

Keys, endpoints, and examples.

RedModel connectedredmodel OPENAI-COMPATIBLE

API keys

Manage access to the model.

Loading your workspace…

Keys belong to your account. 0/10 keys created.
Keep your keys private and use them from a server.

Your API base URL

Loading endpoint…

Set your client’s base URL to this endpoint and use redmodel as the model ID. Both streaming and standard responses are supported.

Quickstart

OpenAI-compatible.

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["REDMODEL_API_KEY"],
    base_url="http://localhost:3000/v1"
)

response = client.chat.completions.create(
    model="redmodel",
    messages=[{
        "role": "user",
        "content": "Challenge my assumptions."
    }]
)

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

pip install openai

Reference

POST/v1/chat/completions

Send a conversation and receive the model’s next response. Authenticate with Authorization: Bearer YOUR_REDMODEL_API_KEY and send a JSON body.

Parameter	Type	Description
`model`	string	Use `redmodel`.
`messages`	array	Messages with role and content. End with a user message.
`stream`	boolean	Set true for server-sent events. Default: false.
`max_tokens`	integer	Optional output limit passed to the model provider.

GET/v1/models

List the available model IDs. Use the same Bearer token as your chat requests. The response follows the OpenAI models-list format.

INFOLimits & response codes

Each key supports up to 60 requests per minute in this prototype. A 429 response includes a Retry-After header. Invalid or missing keys return 401; malformed requests return 400. The demo returns simulated content, so it is intended for integration testing.