API Documentation

An OpenAI-compatible API for the latest GPT & Gemini models.

Get your API key from the Telegram bot @ii_dialog_bot — send /api. Point any OpenAI SDK at the base URL below.

Base URL

https://chat.nano-banana-api.com/v1

Authentication

Authorization: Bearer YOUR_API_KEY

Chat completions

POST /v1/chat/completions — returns a standard OpenAI chat.completion object. Add "stream": true for server-sent events ending with data: [DONE].

curl https://chat.nano-banana-api.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://chat.nano-banana-api.com/v1")

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://chat.nano-banana-api.com/v1" });

const resp = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Models & pricing

USD per 1,000,000 tokens, billed against your balance. List via GET /v1/models.

Model	Input / 1M	Output / 1M
gpt-5.4	$0.42	$3.52
gpt-5.5	$1.30	$7.94
gemini-3.1-pro	$0.88	$4.12
gemini-3.1-flash-lite	$0.14	$0.88
gemini-3.5-flash	$0.70	$5.88
gemini-3-flash	$0.24	$1.76
gemini-3-pro	$0.88	$4.12
gemini-2.5-flash	$0.18	$1.18

HTTP 402 means your balance is empty — top up via @ii_dialog_bot.