Developer docs
NezhaGate Docs
One API key for 35 chat models, 7 image models and 11 video models. OpenAI- and Anthropic-compatible: change one URL and go.
Your first request in three steps
Create an API keySign up, then create one on the API Keys page of the console. The key is shown only once, so copy it.
Create an API key
Set the base URLExisting OpenAI SDK code needs two changes: base_url and api_key.
Base URLhttps://nezhagate.com/v1
Send a requestPut any model ID from the catalogue in model. You pay for what you use; failed requests are never billed.
cURL
curl https://nezhagate.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-flash-0731", "messages": [{"role": "user", "content": "Hello"}]}'
Python · openai
from openai import OpenAI
client = OpenAI(base_url="https://nezhagate.com/v1", api_key="YOUR_API_KEY")
resp = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
Node.js · openai
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://nezhagate.com/v1", apiKey: "YOUR_API_KEY" });
const resp = await client.chat.completions.create({
model: "deepseek-v4-flash-0731",
messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);
Explore the docs
API referenceEvery endpoint, plus parameters, examples and responses for each model.→
User guideSetup, authentication, models and prices, async jobs, balance and error codes.→
IntegrationsStep-by-step setup for Claude Code, Cline, Cherry Studio and more.→
WebhookGet video and image results pushed to your server the moment a job ends.→
FAQBilling, refunds, where the models come from, and reliability.→
ChangelogNew models, price changes and service notices.→
Docs for AI tools
Hand these links to Cursor, Claude Code or ChatGPT and it can write the integration code from the docs.