API Documentation

AI-AllInOne provides a unified, OpenAI-compatible API to access 53+ AI models — including Qwen, DeepSeek, GLM, Kimi, MiniMax, StepFun, and more. Chat, embeddings, rerank, image generation, video generation, ASR, and TTS in one platform.

Quick Start

Get up and running in 3 steps:

Create an Account

Get Your API Key

After logging in, go to the API Keys page and create a key. Your key starts with aak-. New users receive free credits to test the API.

Send Your First Request

Use your key to make a chat completion request:

curl

curl https://ai-allinone.com/v1/chat/completions \
  -H "Authorization: Bearer aak-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OpenAI SDK Compatible

Simply change base_url to https://ai-allinone.com/v1 and use your aak- key. All OpenAI-compatible SDKs (Python, Node.js, Go, etc.) work out of the box.

Try it in the Playground

No code required. Test models interactively in your browser with streaming support, token counting, and latency metrics.

Open Playground →

Authentication

All API requests require authentication via your API key in the Authorization header.

API Key Format

Your API key starts with aak- followed by a random string, e.g. aak-live-x8k2m9f4q7z3.

Header Usage

http

Authorization: Bearer aak-your-key
Content-Type: application/json

Keep Your Key Secure

Never expose your API key in client-side code or public repositories. Use environment variables and server-side proxies in production. You can create and revoke keys at any time from the dashboard.

Base URL

https://ai-allinone.com

All API endpoints are relative to this base URL. The API path prefix is /v1.

Online Playground

The built-in playground lets you test any model directly from your browser — no setup required.

Select from 53+ models with live pricing display
Toggle streaming on/off to see SSE responses in real time
View TTFT (Time To First Token), total latency, and token usage
Custom system prompt support
Use your own API key — requests are billed to your account

Launch Playground →

Chat Completions

POST/v1/chat/completions

Creates a model response for the given chat conversation. Fully compatible with the OpenAI Chat Completions API.

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID from the model list (e.g. `deepseek-v4-flash`, `qwen3.7-max`)
`messages`	array	Yes	Array of message objects with `role` and `content`
`stream`	boolean	No	Enable SSE streaming. Default: `false`
`temperature`	number	No	Sampling temperature (0–2). Default: model-dependent
`max_tokens`	integer	No	Maximum tokens to generate
`top_p`	number	No	Nucleus sampling parameter (0–1)
`response_format`	object	No	Force JSON output with `{"type":"json_object"}`

Example Request

curl

curl https://ai-allinone.com/v1/chat/completions \
  -H "Authorization: Bearer aak-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "stream": false,
    "temperature": 0.7
  }'

Example Response

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "deepseek-v4-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Streaming

Set "stream": true to receive Server-Sent Events (SSE). The response format is identical to OpenAI's streaming format.

Embeddings

POST/v1/embeddings

Creates an embedding vector representing the input text. Compatible with the OpenAI Embeddings API.

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Embedding model: `text-embedding-v4`, `text-embedding-v3`, `qwen3-vl-embedding`, `multimodal-embedding-v1`
`input`	string/array	Yes	Text or array of texts to embed

curl

curl https://ai-allinone.com/v1/embeddings \
  -H "Authorization: Bearer aak-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-v4",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Rerank

POST/v1/rerank

Re-ranks documents based on relevance to a query. Useful for RAG pipelines.

Available Rerank Models

gte-rerank-v2 — GTE Rerank V2
qwen3-rerank — Qwen3 Rerank
qwen3-vl-rerank — Qwen3 VL Rerank (multimodal)

curl

curl https://ai-allinone.com/v1/rerank \
  -H "Authorization: Bearer aak-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gte-rerank-v2",
    "query": "What is DeepSeek?",
    "documents": ["DeepSeek is an AI lab.", "The weather is nice."],
    "top_n": 2
  }'

Video Generation

POST/v1/video/generations

Generates video from text or image prompts.

Available Video Models

Model ID	Name	Tier
`doubao-seedance-2-0-260128`	Seedance 2.0	Premium
`doubao-seedance-2-0-fast-260128`	Seedance 2.0 Fast	Standard
`doubao-seedance-2-0-mini-260615`	Seedance 2.0 Mini	Economy
`doubao-seedance-1-0-pro-250528`	Seedance 1.0 Pro	Premium
`happyhorse-1.1-t2v`	Happy Horse 1.1 T2V	Premium
`happyhorse-1.1-i2v`	Happy Horse 1.1 I2V	Premium

Example

curl

curl https://ai-allinone.com/v1/video/generations \
  -H "Authorization: Bearer aak-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2-0-260128",
    "prompt": "A cat sitting on a windowsill watching rain fall outside"
  }'

Image Generation

POST/v1/images/generations

Generates images from text prompts. Compatible with the OpenAI Images API.

Available Image Models

Model ID	Name	Tier
`wan2.7-image-pro`	Wan 2.7 Image Pro	Premium
`wanx2.1-t2i-plus`	Wanx 2.1 T2I Plus	Standard
`wanx2.1-t2i-turbo`	Wanx 2.1 T2I Turbo	Economy
`wanx2.0-t2i-turbo`	Wanx 2.0 T2I Turbo	Economy
`qwen-image-2.0-pro`	Qwen Image 2.0 Pro	Standard

Speech Recognition & Synthesis

ASR (Speech-to-Text)

Transcribe audio files to text. Billed per second of audio.

fun-asr — Fun ASR Economy
qwen3-asr-flash — Qwen3 ASR Flash Standard
sensevoice-v1 — SenseVoice V1 Standard

TTS (Text-to-Speech)

Synthesize speech from text. Billed per character.

cosyvoice-v3.5-plus — CosyVoice V3.5 Plus Premium
cosyvoice-v3-plus — CosyVoice V3 Plus Standard
cosyvoice-v3-flash — CosyVoice V3 Flash Economy

Model List

All 53 active models. For real-time pricing, see the pricing page. Check system status for availability.

Chat / Language Models Premium

Model ID	Display Name	Context
`qwen3.7-max`	Qwen3.7 Max	1M
`deepseek-v4-pro`	DeepSeek V4 Pro	128K
`glm-5.2`	GLM-5.2	128K
`kimi-k3`	Kimi K3	128K
`qvq-max`	QvQ Max	128K
`qwen3.5-omni-plus`	Qwen3.5 Omni Plus	1M
`qwen3-vl-plus`	Qwen3 VL Plus	256K

Chat / Language Models Standard

Model ID	Display Name
`deepseek-v4-flash`	DeepSeek V4 Flash
`qwen3.7-plus`	Qwen3.7 Plus
`qwen3.6-plus`	Qwen3.6 Plus
`qwen3.6-flash`	Qwen3.6 Flash
`glm-5.1`	GLM-5.1
`glm-5`	GLM-5
`glm-4.7`	GLM-4.7
`kimi-k2.7-code`	Kimi K2.7 Code
`kimi-k2.6`	Kimi K2.6
`kimi-k2.5`	Kimi K2.5
`kimi-k2-thinking`	Kimi K2 Thinking
`MiniMax/MiniMax-M3`	MiniMax M3
`qwen3-coder-plus`	Qwen3 Coder Plus
`qwq-plus`	QwQ Plus
`qwen-long`	Qwen Long
`stepfun/step-3.7-flash`	Step 3.7 Flash

Chat / Language Models Economy

Model ID	Display Name
`qwen3.5-flash`	Qwen3.5 Flash
`qwen3.5-plus`	Qwen3.5 Plus
`qwen3-coder-flash`	Qwen3 Coder Flash
`glm-4.5-air`	GLM-4.5 Air
`MiniMax-M2.5`	MiniMax M2.5
`qwen3-vl-flash`	Qwen3 VL Flash

Programmatic Model List

Fetch the live model list (including all embedding, rerank, image, video, ASR, and TTS models) via:

bash

curl https://ai-allinone.com/api/public/models

Code Examples

Python (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    api_key="aak-your-key",
    base_url="https://ai-allinone.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)

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

Python (Streaming)

python

from openai import OpenAI

client = OpenAI(
    api_key="aak-your-key",
    base_url="https://ai-allinone.com/v1"
)

stream = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

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

Node.js (OpenAI SDK)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "aak-your-key",
  baseURL: "https://ai-allinone.com/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
});

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

Embeddings (Python)

python

from openai import OpenAI

client = OpenAI(
    api_key="aak-your-key",
    base_url="https://ai-allinone.com/v1"
)

response = client.embeddings.create(
    model="text-embedding-v4",
    input="The quick brown fox"
)

print(response.data[0].embedding[:5])  # first 5 dimensions

Error Codes

Code	Meaning	Solution
`400`	Bad request — invalid parameters or model name	Check your request body format and model ID
`401`	Unauthorized — invalid or missing API key	Verify your `aak-` key is correct and active
`402`	Payment required — insufficient balance	Top up your account on the Wallet page
`404`	Not found — model not available	Check the model name. See model list
`429`	Rate limit exceeded	Reduce request frequency
`500`	Internal server error	Retry. If persistent, contact support
`502`	Bad gateway — upstream error	Upstream temporarily unavailable. Wait and retry
`504`	Gateway timeout	Upstream took too long. Retry with simpler prompt

Error Response Format

json

{
  "error": {
    "message": "Insufficient balance. Please top up your account.",
    "type": "insufficient_balance",
    "code": "insufficient_balance"
  }
}

Billing

All API usage is billed in USD based on token/character/second/image consumption, depending on the model type. Pricing is transparent — see the pricing page for per-model rates.

Billing Types

Type	Unit	Models
`token`	Per 1K tokens (input + output)	Chat/Language models
`embedding`	Per 1K input tokens	Embedding models
`rerank`	Per 1K input tokens	Rerank models
`image`	Per image generated	Image generation models
`video`	Per video generated	Video generation models
`audio_second`	Per second of audio	ASR models
`character`	Per character	TTS models

Pay-As-You-Go

No monthly fees, no minimum commitment. You only pay for what you use. Deposit credits via the Wallet page and track your spending in the dashboard.

System Status

Check real-time service health and model availability at ai-allinone.com/status.