API Documentation

OpenAI-compatible API. Use your existing SDK — just change the base URL.

Contents Quick Start Authentication Models & Pricing Chat Completions Error Codes Rate Limits SDK Examples

Quick Start

Base URL: https://api.tunanapi.com/v1
Compatibility: OpenAI API format — works with openai SDK, LangChain, CrewAI, etc.

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.tunanapi.com/v1"
)

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

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

cURL

curl https://api.tunanapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-YOUR_API_KEY',
  baseURL: 'https://api.tunanapi.com/v1'
});

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

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

Authentication

Include your API key in the Authorization header:

Authorization: Bearer sk-YOUR_API_KEY

Get your API key at tunanapi.com — sign up with email and top up credits. New accounts get $0.50 free.

Models & Pricing

All prices per 1M tokens. Input = prompt tokens, Output = completion tokens.

Model	Provider	Input	Output	Context
deepseek-chat	DeepSeek	$0.20	$0.40	128K
deepseek-reasoner	DeepSeek	$2.50	$5.00	128K
qwen3.7-max	Qwen	$1.80	$5.40	128K
qwen3.7-plus	Qwen	$0.58	$1.74	128K
qwen3.5-flash	Qwen	$0.07	$0.22	128K
glm-4-plus	GLM	$1.80	$5.40	128K
glm-4-flash	GLM	$0.07	$0.22	128K
minimax-m2.5	MiniMax	$0.22	$1.65	197K
minimax-m2.7	MiniMax	$0.29	$1.73	205K
minimax-m3	MiniMax	$0.43	$3.31	1M

Choosing a model? Use deepseek-chat for general tasks, deepseek-reasoner for complex reasoning, qwen3.5-flash or glm-4-flash for fast & cheap, and minimax-m3 for long-context (1M tokens).

Chat Completions

POST /v1/chat/completions

Create a chat completion. Compatible with OpenAI's chat completions API.

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (see table above)
`messages`	array	Yes	Array of message objects with `role` and `content`
`temperature`	number	No	0-2, default 1. Higher = more random
`max_tokens`	integer	No	Max tokens in completion
`stream`	boolean	No	Stream partial results (SSE)
`top_p`	number	No	Nucleus sampling, default 1

Streaming Example

from openai import OpenAI

client = OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.tunanapi.com/v1"
)

stream = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Write a haiku about coding"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Error Codes

Code	Type	Description
400	Bad Request	Invalid parameters or malformed request
401	Unauthorized	Invalid or missing API key
402	Insufficient Quota	Not enough credits. Top up at tunanapi.com
404	Not Found	Model not available or endpoint doesn't exist
429	Rate Limited	Too many requests. Slow down or contact us
500	Server Error	Internal error. Retry after a moment
503	Service Unavailable	Upstream provider temporarily down

Insufficient quota? Your balance is deducted per token. When credits run out, requests return 402. Top up at tunanapi.com.

Rate Limits

Default limits per API key:

Limit	Value
Requests per minute	60 RPM
Tokens per minute	~500K TPM
Max context	Depends on model (see table above)

Need higher limits? Contact us.

SDK & Integration Examples

LangChain (Python)

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek-chat",
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.tunanapi.com/v1"
)

response = llm.invoke("Explain quantum computing in one paragraph")
print(response.content)

OpenAI CLI

# Set environment variables
export OPENAI_API_KEY="sk-YOUR_API_KEY"
export OPENAI_BASE_URL="https://api.tunanapi.com/v1"

# Use the CLI
openai api chat_completions.create -m deepseek-chat -g user "Hello!"

Curl — Check Balance

# Check your remaining quota
curl https://api.tunanapi.com/api/user/self \
  -H "Authorization: Bearer sk-YOUR_API_KEY"