aicentosAuthenticity, speed and price analysis

About the site

企业级大模型 API 接入网关
aicentos 是面向开发者与企业的 AI API 中转聚合平台。一个 API Key 统一调用 OpenAI、Anthropic、Google、xAI 等主流大模型;上游为自建官方账号池、直连厂商官方 API,多账号兜底与自动故障转移,可用率实时公开。

Service details

  • Minimum top-upNot provided
  • Sign-up bonus¥1
  • Support responseNot provided
  • Payment methodsAlipay, WeChat Pay, Other
  • China invoiceSupported
  • International invoiceNot supported
  • RefundsSupported
  • PromotionsNot provided
ModeldefaultData security level 0

Comparison summary

No measurements for aicentos yet
The listing, models and prices are on file; this page updates on its own once measurements arrive.

Qwen 3.6 Plus on aicentos: a coding session costs ¥1.92, ranking 1 of 1, the cheapest relay (median ¥1.92).

Authenticity

Model consistency

Output distribution for the same requests on this relay and on the official API · higher is better

No probe results for this route yet
Probe results for the same model on other routes are in the degradation monitor.
Open the degradation monitor
ⓘ Method: see the blog post “Did the model really get dumber?” Read

Speed

Measured by time to first token (seconds) and output speed (tokens / second)

Time to first token

Seconds until the first token · lower is better

No data for aicentos0 relays
No data yet
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
defaultQwen 3.6 PlusNot probed yet¥0.86¥5.14Per million tokens
chinaQwen 3.6 PlusNot probed yet¥0.23¥1.37Per million tokens

Cost per coding session

Qwen 3.6 Plus · 2M input and 40k output tokens (¥) · split by token type · lower is better

1 relays
OutputInput
¥0¥0.5¥1¥1.5¥2¥1.92aicentos
ⓘ USD prices are converted at 1 USD = 6.7698 CNY

Prices: cache hit, input and output

¥ / 1M tokens

Cache hitInputOutput
¥0¥0.5¥1¥1.5¥2¥2.5¥3¥3.5¥4¥4.5¥5¥5.5¥5.14aicentos

Cache

Coding requests repeat much of their context, so the cache hit rate largely decides what you actually pay. Drag the hit rate and the costs and ranking below are reweighted with cache prices.

Cache discount
Not provided
Cache hit — · input ¥0.857143 (per 1M tokens)
Measured hit rate
Pending
Measured by replaying multi-turn sessions: cached-read tokens in usage as a share of all input
Session cost at 80% hit rate
¥1.92
¥1.92 without cache, 0% saved

Cache-weighted session cost

Qwen 3.6 Plus · of 2M input tokens, the hit share is billed at the cache price and the rest at the input price, plus 40k output (¥) · lower is better

Rank 1 / 1
80%Coding agents typically see 70%–90%
Cached inputUncached inputOutput
¥0¥0.5¥1¥1.5¥2¥1.92No cache priceaicentos
ⓘ Routes without a cache price are billed at the input price; cache write fees are not included

Stability

Availability

Request success rate, last 24 hours · higher is better

No data for aicentos0 relays
No data yet

Status of each model, last 24 hours

One cell per hour · green ok, yellow delayed, red failed

No data for aicentos
ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
Claude Haiku 4.5claude———
Gemini 4 Argongemini———
Qwen 3.6 Plusdefault———
Qwen 3.7 Plusdefault———
Kimi K3free———
Claude Sonnet 5claude———
Claude Fable 5claude———
DeepSeek V4 Prodefault———
Claude Opus 4.8claude———
GPT 5.6 Soldefault———
Claude Opus 5claude———
GPT 5.6 Terradefault———
DeepSeek V4 Flashdefault———
Claude Opus 4.6claude———
Claude Opus 4.7claude———
Claude Sonnet 4.6claude———
Gemini 3.8 Flashgemini———
GLM 5.3free———
Gemini 3.1 Pro Previewgemini———
GLM 5.3 Flashdefault———
Gemini 2.5 Flashgemini———
Claude Opus 4.5claude———
Gemini 3 Flash Previewgemini———
Gemini 3.5 Flashgemini———
Gemini 3.6 Flashgemini———
Gemini 3.7 Flashgemini———
Gemini 2.5 Progemini———
Gemini 3 Flashgemini———
Qwen 3.7 Maxdefault———
Qwen 3.8 Flashdefault———

FAQ

How much does Qwen 3.6 Plus cost on aicentos?

Input ¥0.857143 and output ¥5.142857 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥1.92, an API rate of 0.25.

How does the cache hit rate affect price?

aicentos has not published a cache price for this route, so cache hits are billed at the input price.Measured hit rates will replace this assumption once available.

Which models does aicentos support?

Folkbench currently lists 30: Claude Sonnet 5, Claude Fable 5, GPT 5.6 Sol, Claude Opus 5, GPT 5.6 Terra, Kimi K3, DeepSeek V4 Pro, Claude Opus 4.8, Claude Opus 4.6, Claude Opus 4.7, Claude Sonnet 4.6, DeepSeek V4 Flash, Gemini 3.8 Flash, GLM 5.3, Claude Haiku 4.5, Gemini 4 Argon, Gemini 3.1 Pro Preview, GLM 5.3 Flash, Gemini 2.5 Flash, Claude Opus 4.5, Gemini 3 Flash Preview, Gemini 3.5 Flash, Gemini 3.6 Flash, Gemini 3.7 Flash, Gemini 2.5 Pro, Gemini 3 Flash, Qwen 3.7 Max, Qwen 3.8 Flash, Qwen 3.6 Plus, Qwen 3.7 Plus.

What does the data security level mean?

Folkbench rates relays from 0 to 4 based on public policies and verifiable evidence; aicentos is currently level 0. The check covers leaks in responses and error messages only, and does not prove data retention or training policies.

How often is this data updated?

Availability and time to first token use a 24-hour window, and this page syncs live data every 15 minutes.