One API for
China and Global AI

One OpenAI-compatible API for China and global AI models.

Built for global developers who need broader model choice, reliable routing and simple usage-based billing.

Get API Key Learn More
main.py
import os
from openai import OpenAI

client = OpenAI(
  api_key=os.environ["ONEAI_API_KEY"],
  base_url="https://uri/v1",
)

response = client.responses.create(
  model="gpt-5.6-sol",
  input="Say hello in one sentence.",
  stream=False,
)

print(response)
Scroll
ADVANTAGES

Advantages

Broader model choice, one production-ready API

🔒

Global Routing

Reliable routing for responsive model calls across leading AI providers and production workloads.

💳

Usage-Based Billing

Clear, usage-based billing makes it easy to test, scale and manage model costs.

🌐

Unified Models

Use leading China models including Kimi, GLM, HappyHorse, Qwen, Wan, DeepSeek and BytePlus, alongside GPT, Claude and Gemini.

⚡

Multi-Region Reliability

Multi-node routing is continually tuned for responsive, reliable API access across regions.

🔌

OpenAI Compatible

OpenAI-compatible endpoints: usually only change base_url in existing code.

🛟

Dedicated Support

Technical and business support for teams building and scaling with AI.

MODELS

Supported Models

One API key for leading China models and global model choice

DeepSeek V4 Pro
Kimi K3
GLM-5.2
Qwen3.8 Max Preview
Wan 2.7
HappyHorse (HappyHouse)
Seedream 5.0 Pro
Seed 2.1 Turbo
GPT-5.6 (Sol / Terra / Luna)
Claude Sonnet 5
Gemini 3.5 Flash
ChatGPT Images 2.0

China AI Model Highlights

Kimi K3

Up to 1M context with native vision and configurable reasoning for coding, knowledge work and agent tasks.

Provider documentation

GLM-5.2

1M context, up to 128K output, plus function calling and structured output for long-running development workflows.

Provider documentation

Qwen3.8 Max Preview

1M context with reasoning, function calling and built-in tools. This model remains in preview.

Provider documentation

DeepSeek V4 Pro

1M context, up to 384K output, tool calls and thinking modes for agentic and reasoning workloads.

Provider documentation

Wan & HappyHorse

Image and video generation options for creative media workflows, alongside text and reasoning models.

Provider documentation
25+

Supported models

99.9%

Availability

<100ms

Avg latency

7×24

Chinese support

PRICING

Transparent Pricing

Provider reference prices with the billing unit shown for each model

Text: currency per 1M tokens · Media: CNY per generated second
China AI Models

Kimi / GLM / Qwen / Wan / HappyHorse / BytePlus / DeepSeek

China models
ModelsInputOutput
Leading China Models
GLM-5.2glm-5.2CNY 8CNY 2 cache hitCNY 28
Wan 2.7 T2Vwan2.7-t2vN/AOutput-only billingCNY 0.733924/s720P international · 1080P: CNY 1.100886/s
HappyHorse 1.1 T2Vhappyhorse-1.1-t2vN/AOutput-only billingCNY 0.90/s720P global list price · 1080P: CNY 1.20/s
Seedream 5.0 Prodola-seedream-5-0-proFree first imageThen USD 0.003/imageUSD 0.045/imageUp to 2.36M pixels · USD 0.09 above
Seed 2.1 Turbodola-seed-2-1-turboUSD 0.50USD 0.10 cache hitUSD 2.50
Qwen3.8 Max Previewqwen3.8-max-previewToken Plan onlyNo PAYG token rate publishedSee plan
Kimi K3kimi-k3CNY 20CNY 2 cache hitCNY 100
DeepSeek V4 Prodeepseek-v4-proUSD 0.435USD 0.003625 cache hitUSD 0.87
GLM Kimi Qwen Wan / HappyHorse BytePlus DeepSeek
*Provider reference prices checked Jul 22, 2026. Promotions, regions and model availability may change.
Anthropic

Claude

8 models
ModelsInputOutput
Latest Models
Claude Sonnet 5claude-sonnet-5$2introductory through Aug 31, 2026$10
Claude Haiku 4.5claude-haiku-4-5$1$5
Expand legacy models 6 historical models
ModelsInputOutput
Claude Opus 4.6claude-opus-4-6$5$25
Claude Sonnet 4.5claude-sonnet-4-5$3$15
Claude Opus 4.5claude-opus-4-5$5$25
Claude Opus 4.1claude-opus-4-1$15$75
Claude Sonnet 4claude-sonnet-4$3$15
Claude Haiku 3claude-3-haiku$0.25$1.25
Official pricing
*Prices are reference values. Please check official pricing for updates
Google

Gemini

10 models
ModelsInputOutput
Gemini 3 Series
Gemini 3.5 Flashgemini-3.5-flashSee official pricingStable model for agentic and coding tasksSee official pricing
Gemini 3.1 Progemini-3.1-pro-preview$2> 200k input tokens: $4Input: text / image / video / audio$12> 200k input tokens: $18Text output
Gemini 3.1 Flash Imagegemini-3.1-flash-image-preview$0.50Input: text / image$3Image output: $60
Gemini 3.1 Flash-Litegemini-3.1-flash-lite-preview$0.25Audio input: $0.50$1.50
Gemini 3 Progemini-3-pro-preview$2> 200k input tokens: $4$12> 200k input tokens: $18
Gemini 3 Flashgemini-3-flash-preview$0.50Audio input: $1$3
Expand specialized capabilities Image generation, Computer Use, Live API, etc.
ModelsInputOutput
Gemini 3 Pro Imagegemini-3-pro-image-preview$2Input: text / image$12Image output: $120
Gemini 2.5 Pro Computer Usegemini-2.5-pro-computer-use-preview-1025$1.25> 200k input tokens: $2.50$10> 200k input tokens: $15
Gemini 2.5 Flash Imagegemini-2.5-flash-image$0.30Input: text / image$2.50Image output: $30
Gemini 2.5 Flash Live APIgemini-2.5-flash-liveText $0.5Audio $3 / video and image $3Text $2Audio $12
Expand Gemini 2.5 models Pro / Flash / Flash Lite
ModelsInputOutput
Gemini 2.5 Progemini-2.5-pro$1.25> 200k input tokens: $2.50$10> 200k input tokens: $15
Gemini 2.5 Flashgemini-2.5-flash$0.30Audio input: $1$2.50
Gemini 2.5 Flash Litegemini-2.5-flash-lite$0.10Audio input: $0.30$0.40
Official pricing
*Prices are reference values. Please check official pricing for updates
OpenAI

GPT

40+ models
ModelsInputOutput
Latest Flagship Models
GPT-5.6Sol / Terra / LunaSee official pricingThree model tiersSee official pricing
Expand GPT Series GPT-5.5 / GPT-5.4 / GPT-5.2 / GPT-5 / GPT-4.1 / GPT-4o
ModelsInputOutput
GPT-5.5gpt-5.5$5.00$30.00
GPT-5.4gpt-5.4$2.50Long > 272k: $5.00$15.00Long > 272k: $22.50
GPT-5.2gpt-5.2$1.25$10.00
GPT-5gpt-5$1.25$10.00
GPT-5 Minigpt-5-mini$0.25$2.00
GPT-5 Nanogpt-5-nano$0.05$0.40
GPT-4.1gpt-4.1$2.00$8.00
GPT-4ogpt-4o$2.50$10.00
GPT-4o Minigpt-4o-mini$0.15$0.60
Expand realtime / audio models Realtime, Audio Preview, etc.
ModelsInputOutput
GPT-Realtime-2gpt-realtime-2Audio $32.00cached audio $0.40Audio $64.00
GPT-Realtime 1.5gpt-realtime-1.5Audio $32.00Text $4.00 / Image $5.00Audio $64.00Text $16.00
GPT-Realtime Minigpt-realtime-miniAudio $10.00Text $0.60 / Image $0.80Audio $20.00Text $2.40
GPT-Audiogpt-audioAudio $32.00Text $2.50Audio $64.00Text $10.00
Expand image / transcription / reasoning models Image, Transcription, O Series
ModelsInputOutput
ChatGPT Images 2.0chatgpt-image-latestImage $8.00Text $5.00Image $32.00Text $10.00
GPT-Image 1.5gpt-image-1.5Image $8.00Text $5.00Image $32.00Text $10.00
GPT-Image 1 Minigpt-image-1-miniImage $2.50Text $2.00Image $8.00
Transcription Models
GPT-4o Transcribegpt-4o-transcribe$2.50$10.00
GPT-4o Mini Transcribegpt-4o-mini-transcribe$1.25$5.00
O Series
o4-minio4-mini$1.10$4.40
o3o3$2.00$8.00
o3-proo3-pro$20.00$80.00
Official pricing
*Prices are reference values and aligned with the current page model names. Please check official pricing for updates
QUICK START

Quick Start

Integrate in four steps and start using the API right away

1
STEP 01

Create Account

Register and verify your account

2
STEP 02

Top Up

Alipay / WeChat Pay

3
STEP 03

Get API

Create an API key in one click

4
STEP 04

Start Calling

Change base_url and call

# Install SDK

pip install openai

# Set API key
export ONEAI_API_KEY="your-api-key"

# Send request

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ONEAI_API_KEY"],
    base_url="https://uri/v1",
)

response = client.responses.create(
    model="gpt-5.6-sol",
    input="Say hello in one sentence.",
    stream=False,
)

print(response)
RESOURCES

Developer Resources

Everything you need to get started

📚

Docs

API references and tutorials
💬

Developer Group

Community discussion
🔬

Playground

Online testing and debugging
📝

Blog

Technical articles

Ready to start?

Get an API key and start building with China and global AI models

Get API Key