Brevy API Documentation

Getting Started

The Brevy API uses an OpenAI-compatible interface. You can use any OpenAI-compatible SDK, library, or tool by pointing it to our API base URL and using your Brevy API key.

1. Create an API Key

Go to your Dashboard → API Integrations → Create API Key. Your key will look like brevy-v1-xxxx....

2. Set your API Base URL

https://brevy.brevios.com/v1

3. Make your first request

curl

curl https://brevy.brevios.com/v1/chat/completions \
  -H "Authorization: Bearer brevy-v1-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-ultra-free",
    "messages": [
      {"role": "user", "content": "Write a Python function to reverse a string"}
    ],
    "temperature": 0.7
  }'

Authentication

Every request must include your API key in the Authorization header:

Authorization: Brevy-v1-your-api-key

API keys are scoped to your account and respect your plan's rate limits. You can create up to 10 API keys from the dashboard.

⚠️ Keep your API key secret. Never commit it to version control or expose it in client-side code. If compromised, revoke it immediately from the dashboard and create a new one.

Base URL

GET https://brevy.brevios.com/v1

All API endpoints are relative to this base URL.

Endpoints

POST /v1/chat/completions

Create a chat completion. Send messages and get AI-generated responses.

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (see available models)
`messages`	array	Yes	Array of message objects with `role` and `content`
`temperature`	number	No	Sampling temperature (0-2). Default: 1
`top_p`	number	No	Nucleus sampling (0-1). Default: 1
`stream`	boolean	No	Enable streaming responses. Default: false
`thinking`	boolean	No	Enable extended thinking (for supported models)

GET /v1/models

List all available models.

Available Models

Models are selected based on your plan. Access the model list via the GET /v1/models endpoint or check the dashboard.

Model ID	Name	Type
`nemotron-3-ultra-free`	Nemotron 3 Ultra Free	Free
`mimo-v2.5-free`	MiMo-V2.5 Free	Free
`deepseek-v4-flash-free`	DeepSeek V4 Flash Free	Free

Lite and Pro plans unlock additional models. See the dashboard for your full model list.

Rate Limits

API rate limits depend on your plan. Limits reset every minute (RPM / TPM) and every day (RPD).

Plan	Requests/Min	Requests/Day	Tokens/Min
Free	10	1,000	100,000
Lite	25	5,000	300,000
Pro	50	10,000	700,000

Rate limit headers are returned with every response:

X-RateLimit-Limit: 50
X-RateLimit-Remaining: 48
X-RateLimit-Reset: 60

Streaming

Enable streaming by setting "stream": true in your request. The response will be delivered as Server-Sent Events (SSE).

Python

import openai

client = openai.OpenAI(
    api_key="brevy-v1-your-api-key",
    base_url="https://brevy.brevios.com/v1"
)

stream = client.chat.completions.create(
    model="nemotron-3-ultra-free",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Error Handling

Status	Code	Description
400	bad_request	Invalid request parameters
401	unauthorized	Invalid or missing API key
402	insufficient_credits	Not enough credits. Buy more credits.
403	model_not_allowed	Model not available on your plan
429	rate_limit_exceeded	Too many requests. Check `X-RateLimit-Reset` header.
500	server_error	Internal server error. Retry after a moment.

SDKs & Libraries

Use any OpenAI-compatible SDK. Just change the base URL and API key.