📖 EVEZ AI API Documentation

OpenAI-compatible API • 49 models • $0/month

Base URL

https://evez-provider-production.up.railway.app/v1

Authentication

Include your API key in the Authorization header:

Authorization: Bearer evez-admin-0c1bb1e7

Quick Start

import openai

client = openai.OpenAI(
    base_url="https://evez-provider-production.up.railway.app/v1",
    api_key="evez-admin-0c1bb1e7"
)

# Chat completion
response = client.chat.completions.create(
    model="glm-5.1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the 37% theorem?"}
    ],
    max_tokens=500,
    temperature=0.7
)
print(response.choices[0].message.content)

Endpoints

GET /v1/models

List all available models.

POST /v1/chat/completions

Create a chat completion. Compatible with OpenAI API.

{
  "model": "glm-5.1",
  "messages": [{"role": "user", "content": "Hello"}],
  "max_tokens": 100,
  "temperature": 0.7
}

GET /health

Health check endpoint.

Available Models

Model ID	Backend	Context

Backends

Backend	Models	Cost	Latency
Vultr Inference	GLM-5.1, DeepSeek-V3, Kimi-K2, MiniMax-M2	$0.008/1K	~200ms
OpenRouter	26 free models	Free	~500ms
Groq	5 free models	Free	~50ms
HuggingFace	8 models	Free (monthly credits)	~1s
EVEZ Custom	evez-smart, evez-code, evez-fast, evez-vision	Free	N/A

Error Handling

The API returns standard OpenAI-compatible error responses:

{
  "error": {
    "message": "Model not found",
    "type": "invalid_model"
  }
}

Rate Limits

Default: 60 requests/minute. Contact us for higher limits.

GitHub • Donate • Press Kit