API Docs

OpenAI-compatible API. Change one line of code and you're connected.

Quick Start

Prerequisites

Create an account (no credit card needed)
Get your API key from the Console

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://gptapi.net.cn/v1",
    api_key="sk-your-key-here"
)

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

curl https://gptapi.net.cn/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gptapi.net.cn/v1",
  apiKey: "sk-your-key-here",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-pro",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Models & Pricing

All prices in USD per 1M tokens. Pay-as-you-go, no subscription.

Model	Provider	Input/1M	Output/1M	Context
deepseek-v4-pro	DeepSeek	$0.60	$1.80	1M
deepseek-v4-flash	DeepSeek	$0.20	$0.85	1M
kimi-k3	Moonshot	$3.00	$12.00	128K
kimi-k2.7-code	Moonshot	$1.20	$3.60	128K
moonshot-v1-128k	Moonshot	$0.80	$2.40	128K
moonshot-v1-32k	Moonshot	$0.50	$1.50	32K
moonshot-v1-8k	Moonshot	$0.25	$0.75	8K
qwen3.7-max	Alibaba	$1.20	$3.50	128K
qwen3.7-plus	Alibaba	$0.25	$0.78	128K
qwen-image-2.0-pro	Alibaba	$2.00	$6.00	-
qwen3.7-text-embedding	Alibaba	$0.01	$0.01	-
doubao-pro-128k	ByteDance	$1.00	$4.50	128K
doubao-lite-32k	ByteDance	$0.10	$0.30	32K
glm-5.2	Zhipu	$0.80	$2.40	128K

View all models →

Endpoints

Chat Completions

POST https://gptapi.net.cn/v1/chat/completions

Fully compatible with the OpenAI Chat Completions API. Supports streaming, tools/function calling, and all standard parameters.

Image Generation

POST https://gptapi.net.cn/v1/images/generations

Use with qwen-image-2.0-pro. Supports standard OpenAI image generation parameters.

Embeddings

POST https://gptapi.net.cn/v1/embeddings

Use with qwen3.7-text-embedding.

List Models

GET https://gptapi.net.cn/v1/models

Returns all available models with IDs and metadata.

Vision (Image Input)

Supported models: kimi-k3, moonshot-v1-128k-vision-preview, moonshot-v1-32k-vision-preview, moonshot-v1-8k-vision-preview

curl https://gptapi.net.cn/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "kimi-k3",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this image?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
      ]
    }]
  }'

Billing

Payment: Credit/debit cards via Stripe
Minimum Top-up: $10
Pricing: Per-token, no monthly subscription
Unused balance: Never expires

Official Quality Guarantee

Unlike some API gateways that route your requests through quantized or lower-quality model versions, Express API connects directly to official vendor APIs. You always get the exact model you pay for — full precision, no compression, no surprises.

✅ 100% official APIs — Direct connection to DeepSeek, Moonshot, Alibaba, ByteDance, and Zhipu
✅ No quantization — Full model precision, never a 4-bit or 8-bit compressed version
✅ Same provider every time — You always hit the official endpoint, not a random third-party proxy
✅ Kimi K3 at $12/1M output — 20% cheaper than other gateways that sell the same model at $15

Need Help?

Email: support@gptapi.net.cn