📖 API Documentation

API Cup is an OpenAI-compatible API gateway. If your code already works with OpenAI, it works with API Cup — just change the base URL and API key.

Overview

API Cup gives you access to 80+ models from 10+ top AI providers through a single, unified endpoint. Text, vision, code, reasoning, TTS, image generation, and speech recognition — all OpenAI-compatible.

Supported Formats

Format	Endpoint	Status
Chat Completions	`/v1/chat/completions`	✅ All text & vision models
Text-to-Speech	`/v1/audio/speech`	✅ 5 voices (Qwen CosyVoice)
Image Generation	`/v1/images/generations`	✅ 3 quality levels
Speech Recognition	`/v1/audio/transcriptions`	✅ Paraformer
List Models	`/v1/models`	✅ OpenAI-compatible

Authentication

All API requests require an API key. Get yours from the Keys page after signing up.

Authorization: Bearer sk-your-api-key-here

🔐 Security: Never expose your API key in client-side code. Use environment variables or a backend proxy.

Base URL

https://apicup.com

All endpoints are relative to this base URL. If you are using the OpenAI Python SDK:

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-key-here",
    base_url="https://apicup.com/v1"
)

Quickstart

cURL

curl https://apicup.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-key-here" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-key-here",
    base_url="https://apicup.com/v1"
)

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

print(response.choices[0].message.content)

JavaScript / Node.js

import OpenAI from "openai";

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

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

console.log(response.choices[0].message.content);

Chat Completions

POST /v1/chat/completions

OpenAI-compatible chat completions. Supports streaming, system prompts, and multi-turn conversations.

Parameters

Parameter	Type	Required	Description
`model`	string	✅	Model name (e.g. `deepseek-chat`)
`messages`	array	✅	Array of message objects
`stream`	boolean		Enable SSE streaming (default: false)
`temperature`	float		0 - 2. Controls randomness
`max_tokens`	integer		Max tokens in response

Recommended Models

Model	Best For	Input Price	Output Price
`deepseek-chat`	General purpose	$0.34/M	$1.36/M
`deepseek-v4-pro`	Complex reasoning	$1.10/M	$4.40/M
`qwen3.7-max`	Chinese & multilingual	$2.40/M	$9.60/M
`kimi-k2.7-code`	Code generation	$3.32/M	$13.28/M
`glm-5.2`	Chinese reasoning	$2.48/M	$14.88/M
`qwen3.5-flash`	Cheapest option	$0.08/M	$0.80/M

List Models

GET /v1/models

Returns all available models. OpenAI-compatible response format.

curl https://apicup.com/v1/models \
  -H "Authorization: Bearer sk-your-key-here"

Text-to-Speech

POST /v1/audio/speech

OpenAI-compatible TTS. 5 Chinese voices powered by Qwen CosyVoice.

curl https://apicup.com/v1/audio/speech \
  -H "Authorization: Bearer sk-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-tts-longchen",
    "input": "你好，欢迎使用API Cup。",
    "voice": "longchen"
  }' --output speech.mp3

Available Voices

Voice ID	Model Name	Description
`longchen`	`qwen-tts-longchen`	Male, general-purpose
`longwan`	`qwen-tts-longwan`	Female, warm
`longjing`	`qwen-tts-longjing`	Female, newscaster
`longhua`	`qwen-tts-longhua`	Male, mature
`longyu`	`qwen-tts-longyu`	Male, lively

Image Generation

POST /v1/images/generations

OpenAI-compatible image generation. Powered by Qwen Wanx.

curl https://apicup.com/v1/images/generations \
  -H "Authorization: Bearer sk-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-fast",
    "prompt": "A cute orange cat sitting on a cloud, anime style",
    "n": 1,
    "size": "1024x1024"
  }'

Quality Levels

Model	Speed	Price
`qwen-image-fast`	~5s	$0.15 / image
`qwen-image-standard`	~15s	$0.15 / image
`qwen-image-hd`	~30s	$0.40 / image

Speech Recognition

POST /v1/audio/transcriptions

OpenAI-compatible speech-to-text. Powered by Qwen Paraformer.

curl https://apicup.com/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-key-here" \
  -F "file=@audio.mp3" \
  -F "model=qwen-asr-paraformer"

Pricing

You pay per token. No monthly fees, no minimums. Top up with crypto (USDC, USDT, BTC, ETH, SOL) on the Payment page.

1 USD = 500,000 tokens. See the Pricing page for all model prices, or call /v1/models for pricing metadata.

Error Codes

HTTP Code	Meaning
`200`	Success
`400`	Bad request — check your parameters
`401`	Invalid or missing API key
`402`	Insufficient balance — top up your account
`429`	Rate limited — slow down
`500`	Server error — contact support if persistent

Contact

Questions? Issues? Feature requests?

📧 fordeman@proton.me