One endpoint for every major AI model
We supply 739 model APIs to companies building AI products: GPT, Claude, Gemini, DeepSeek and Qwen, all called through one OpenAI-compatible endpoint.
- 739 models
- OpenAI-compatible
- Pay as you go, no monthly fee
Works with
- Dify
- FastGPT
- n8n
- LangChain
- LlamaIndex
- Cherry Studio
- DeepChat
- LobeChat
- AQBot
Quick start
Four steps to 739 models through one endpoint
API example
OpenAI-compatiblehttps://www.tutujin.com/v1/chat/completionsRequest
curl https://www.tutujin.com/v1/chat/completions \
-H "Authorization: Bearer $TUTUJIN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash",
"messages": [
{"role": "user", "content": "Introduce yourself in one sentence"}
]
}'Response
{
"model": "deepseek-v4.1-flash",
"choices": [{
"message": {
"role": "assistant",
"content": "I'm an AI assistant for writing, translation and Q&A."
},
"finish_reason": "stop"
}],
"usage": { "prompt_tokens": 16, "completion_tokens": 46 }
}Priced at deepseek-v4.1-flash in the China Models group: ¥2.8 input, ¥11.2 output per 1M tokens
https://www.tutujin.com/v1/responsesRequest
curl https://www.tutujin.com/v1/responses \
-H "Authorization: Bearer $TUTUJIN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"input": "Introduce yourself in one sentence"
}'Response
{
"model": "gpt-6.1-sol",
"output": [{
"type": "message",
"content": [{
"type": "output_text",
"text": "I'm an AI assistant for writing, translation and Q&A."
}]
}],
"usage": { "input_tokens": 14, "output_tokens": 52 }
}Priced at gpt-6.1-sol in the Standard group: ¥4 input, ¥20 output per 1M tokens
Sample data: latency and token counts are for illustration; the cost uses the model's real price.
How to get started
Top up
Top up online in the console (as shown there), or buy redemption codes offline through support. You pay per use, with no monthly fee.
Console · Top upTop upCreate an API key
Create separate keys per project or customer. Each key can have its own spending cap, expiry date, model allowlist and IP allowlist, and uses the group you assign.
Console · API keysCreate a keyChoose models
Filter Models & pricing by vendor and type, compare group prices and copy the model ID.
Models & pricingBrowse modelsConnect your app
Point base_url at our endpoint and add your key. The official OpenAI, Claude and Gemini SDKs work as they are, so there's no code to rewrite.
DocsRead the docs
Console
One console for usage and spend
Every call is logged with its model, token count and cost. The dashboard totals spend by day and ranks usage by model.
Dashboard
Last 30 days · sample account
82,000
¥384.44
159.1M
1.9
Spend trend
Daily avg ¥12.81 · peak ¥16.70
Top models
By spend
- deepseek-v4.1-flash56.3%
- gemini-3.8-flash19.8%
- qwen3.5-plus19.4%
- claude-haiku-5-53.2%
- text-embedding-3-large1.3%
Why Tutujin
Why choose Tutujin
The model capabilities and business scenarios you need behind one endpoint, with prices, routes and availability you can check yourself.
Quick to integrate
OpenAI-compatible, plus native Claude and Gemini endpoints. Swap in the base_url and key to start; switching models is a change of the model parameter.
Quick startTransparent pricing
Every model's price in every group is public, with input, output and cache priced separately. Pay as you go, no monthly fee.
PricingPublic availability
Success rate and latency of every route of popular models over the last 24 hours, on the public status page.
StatusProcurement and invoices
Top up online or buy redemption codes offline. We issue both China domestic invoices (fapiao) and overseas invoices; request one on WeChat.
Enterprise
Capabilities
Text, image, music and video, speech and embedding models, all through one endpoint
Use cases
Reference setups for common business tasks, with recommended models and cost estimates
AI customer service
Intent detection, retrieval, streamed replies and handoff to people
Enterprise knowledge base and RAG
Document Q&A with embeddings, rerank and a chat model
Document parsing and data extraction
Contracts, invoices and scans turned into structured data
Bulk content production
Product descriptions and marketing copy in bulk, then spot-checked
AI features for SaaS products
A key per tenant, with caps, reconciliation and fallback models
FAQ
Questions people ask before integrating
Can't find your answer? Ask our support team.
What is Tutujin API?
We supply model APIs to companies that build AI products: 739 models including GPT, Claude, Gemini, DeepSeek and Qwen, all called through one OpenAI-compatible endpoint. We don't build end-user AI apps ourselves.
How is it billed? Is there a monthly fee or minimum spend?
You pay as you go. There is no monthly fee and no minimum spend commitment, and ¥1 buys ¥1 of credit. Chat models are billed per token, with input, output and cache reads/writes priced separately; per-request models such as image generation are billed per request.
Why does one model have several prices?
A model usually sits in several groups, and each group is a different route: official relay, cloud provider, or mixed sources that include non-official ones. Different sources mean different prices. Every group is labelled with its source, and you choose one when you create an API key.
Which API formats are supported?
The OpenAI-compatible format (Chat Completions and Responses), Claude's native /v1/messages and Gemini's native generateContent. Image generation and editing, embeddings, rerank, speech and transcription are available too.
Where can I see what each call cost?
The Logs page in the console lists every call with its model, token count and cost.
Can I limit what an API key can spend or call?
Yes. Each key can have its own spending cap, expiry date, model allowlist and IP allowlist, and it uses the group you assign.
Do you store the content of my requests?
Usage logs record call details only: time, model, group, key name, token counts, cost and latency. Request and response bodies are not written to usage logs. To generate a response, your request is forwarded to the model provider behind the group you chose. See the Security & compliance page for details.
How do I top up? Can companies buy in bulk?
Top up online (as shown in the console) or buy redemption codes offline through support. For bulk purchases, add our support on WeChat.
Can you issue invoices?
Yes. We issue both China domestic invoices (fapiao) and overseas invoices: add our WeChat support and send your order number.
Get started
Connect to 739 AI models today
Pay as you go, no monthly fee. For procurement, invoices or integration help, add our support on WeChat.