Skip to content
TutujinAPI

Billing

Pay for usage, with a record of every call

No monthly fee and no minimum spend commitment. ¥1 buys ¥1 of credit, and every charge is listed on the console's Usage page.

  • Pay as you go
  • No monthly fee or minimum spend
  • ¥1 = ¥1 of credit
  • Every call itemized

Where to find unit prices

Unit prices for every model in every group are public on the models page, in ¥ per 1M tokens or ¥ per request.

Prices updated Nov 12, 2026, 8:17 PM

See model prices

How billing works

Per token

Chat, embedding and similar models are billed per token. Input (what you send) and output (what the model generates) are priced separately, in ¥ per 1M tokens.

Per request

Per-request models such as image generation charge once per request regardless of tokens, in ¥ per request.

Cost of one call

input tokens × input price + output tokens × output price + cache read/write cost

Prices are per 1M tokens. For per-request models, cost = unit price × number of requests.

Each call is charged at the price in effect when it is made; price changes only affect later calls.

Cache pricing

Cache reads

Input tokens that hit the context cache are billed at the cache-read price, which is usually far below the normal input price.

Cache writes

Some models charge a cache-write price when content is written to the cache. Each model's detail page shows whether it has cache prices and what they are.

When caching pays off

  • A long, fixed system prompt
  • The same document referenced again and again
  • Long multi-turn conversations

For example, gpt-6.1-sol in the Standard group: input ¥4, cache read ¥0.2, both per 1M tokens.

Groups, and how to choose one

A model usually sits in several groups. Each group is a different route with its own source and price. You pick one group for each API key you create.

Customer-facing, source matters

Prefer groups labelled Official or Cloud.

Internal tools and offline batch jobs

If budget comes first, the cheaper Mixed groups are an option; they include non-official sources.

Chinese models

Use the China Models group for DeepSeek, Qwen, Kimi, GLM, MiniMax and others.

Keep workloads apart

Create one key per product or environment, each with its own group and spending cap.

One model, priced in each of its groups · gpt-6.1-sol¥ per 1M tokens
One model, priced in each of its groupsInputOutput
StandardMixed sourcesCheapest¥4¥20
AzureCloud¥4¥20
Azure PlusCloud¥6¥30
OpenAI DirectOfficial¥9¥45
OpenAI Direct PlusOfficial¥12¥60
Official · EnterpriseOfficial¥21.9¥109.5

All 18 groups

  • StandardLowest priceMixed sources603 modelsCovers every model at the lowest price; some GPT and Claude routes are non-official
  • AzureCloud116 modelsMicrosoft Azure OpenAI — official, well priced, enterprise-grade
  • Azure PlusCloud135 modelsPremium Azure OpenAI line with o-series reasoning models
  • OpenAI DirectOfficial169 modelsOpenAI's own API
  • OpenAI Direct PlusOfficial174 modelsThe fastest, steadiest OpenAI line, incl. o-series and realtime
  • Official · EnterpriseOfficial309 modelsEnterprise line at official list prices, sourced from OpenAI and Anthropic, stability first
  • Claude DirectOfficial47 modelsAnthropic's own API; new models may have limited concurrency at launch
  • Claude List PriceOfficial47 modelsAnthropic official line billed at list price
  • Claude PlusMixed sources40 modelsCost-effective Claude line; includes non-official sources, prices may change
  • Claude LiteMixed sources27 modelsThe cheapest Claude line, non-official sources
  • Gemini PlusOfficial70 modelsGoogle Gemini official line with video understanding
  • Gemini High TierOfficial70 modelsHigher-quota Google Gemini official line
  • China ModelsLowest price—195 modelsDeepSeek, Qwen, Kimi, GLM, MiniMax and more at special prices
  • China Models 2—18 modelsBackup line for Chinese models
  • Economy (per token)Mixed sources42 modelsNon-official sources, billed per token at a discount
  • Economy (per call)Mixed sources54 modelsNon-official sources, billed per call — good for long prompts
  • Stable Diffusion—5 modelsStable Diffusion image models
  • Video Line 1Mixed sources6 modelsVeo and Grok video generation; non-official sources

Worked cost example

Calculated live from current prices (updated Nov 12, 2026, 8:17 PM). Actual charges are whatever the Usage page in the console shows.

Per token: one customer-service turn

gpt-6.1-sol, Standard group. Prices per 1M tokens: input ¥4, output ¥20, cache read ¥0.2.

The request sends 3,000 input tokens, 2,000 of them cache hits, and gets 500 output tokens.

ItemCost
Input (not cached)1,000 × ¥4 ÷ 1,000,000¥0.004
Input (cache read)2,000 × ¥0.2 ÷ 1,000,000¥0.0004
Output500 × ¥20 ÷ 1,000,000¥0.01
Total per call¥0.0144

At 10,000 calls a month, that is about ¥144.

Per request: image generation calls

gpt-image-2, Standard group, ¥0.12 per request.

100 requests cost ¥12.

Top-ups

Top up online (as shown in the console) or buy redemption codes offline through support.

¥1 buys ¥1 of credit. Credit is drawn down by actual usage, with no monthly fee and no minimum spend commitment.

Invoices

We can issue invoices: add our WeChat support and send your order number. For China domestic fapiao, contact us to discuss.

Usage and records

The console shows where every yuan went.
Usage
Time, model, group, token counts and cost for every call.
Per-key caps
Give each key a spending cap and an expiry date to control each project's spend.
Top-up history
Amount and time of every top-up.
Open the console

Check the prices, then choose your groups

Every model and group price is public. For bulk purchases or invoices, add our support on WeChat.

See model pricesContact us
Tutujin support WeChat QR code
WeChatJsnonoChat

Scan the code or search the WeChat ID to add us