金石APIAuthenticity, speed and price analysis

About the site

金石 API 是面向开发者与 AI 工具用户的多模型 API 聚合平台,尽力提供低价而稳定高效的API服务。通过统一入口接入多种 AI 模型,自由选择模型和渠道分组,并在控制台查看调用记录、额度消耗与模型响应信息。从日常对话、辅助编程到应用开发,让模型接入与调用管理更方便、费用更清楚。

Service details

  • Minimum top-up¥1
  • Sign-up bonusNot provided
  • Support responseNot provided
  • Payment methodsAlipay, WeChat Pay
  • China invoiceConditional
  • International invoiceNot verified
  • RefundsNot verified
  • PromotionsNot provided
ModelClaude-CC4Data security level 0

Comparison summary

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

Claude Opus 4.6 on 金石API: a coding session costs ¥3.30, ranking 1 of 3, the cheapest relay (median ¥11.0).

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 金石API0 relays
No data yet
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
Claude-CC4Claude Opus 4.6Not probed yet¥1.50¥7.50Per million tokens
Claude-Max-API蒸馏Claude Opus 4.6Not probed yet¥12.50¥62.50Per million tokens
Claude-CursorClaude Opus 4.6Not probed yet¥2.25¥11.25Per million tokens
Claude-CC2Claude Opus 4.6Not probed yet¥4.00¥20.00Per million tokens
Claude-CCClaude Opus 4.6Not probed yet¥3.50¥17.50Per million tokens
Claude-MaxClaude Opus 4.6Not probed yet¥5.50¥27.50Per million tokens
Claude-Max-0Claude Opus 4.6Not probed yet¥9.50¥47.50Per million tokens
Claude-ProClaude Opus 4.6Not probed yet¥5.00¥25.00Per million tokens

Cost per coding session

Claude Opus 4.6 · 2M input and 40k output tokens (¥) · split by token type · lower is better

3 relays
OutputInput
ⓘ USD prices are converted at 1 USD = 6.7698 CNY

Prices: cache hit, input and output

¥ / 1M tokens

Cache hitInputOutput

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 ¥1.5 (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
¥3.30
¥3.30 without cache, 0% saved

Cache-weighted session cost

Claude Opus 4.6 · 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 / 3
80%Coding agents typically see 70%–90%
Cached inputUncached inputOutput
ⓘ 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 金石API0 relays
No data yet

Status of each model, last 24 hours

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

No data for 金石API
ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
GPT 4.1GPT-Azure———
GPT 4.1 MiniGPT-Azure———
GPT 5 NanoGPT-Azure———
GPT 5GPT-Azure———
GPT-4oGPT-Azure———
Claude Haiku 4.5Claude-Max-API蒸馏———
GPT-4o MiniGPT-Azure———
Gemini 4 ArgonGemini———
DeepSeek V4 ProDeepSeek-华为———
Claude Sonnet 5Claude-CC4———
Kimi K3Kimi-Cyber———
GPT 5.6 Terragpt-enterprise———
Claude Fable 5Claude-Max-API蒸馏———
GPT 5.6 SolGPT-不降智2———
Claude Opus 5Claude-CC4———
Claude Opus 4.7Claude-CC4———
Claude Opus 4.8Claude-CC4———
Claude Opus 4.6Claude-CC4———
Claude Sonnet 4.6Claude-CC4———
Gemini 3.8 FlashGemini———
GLM 5.3Cyber-Pro———
Claude Sonnet 4.5Claude-Max———
Claude Opus 4.5Claude-Max———
Gemini 2.5 FlashGemini———

FAQ

How much does Claude Opus 4.6 cost on 金石API?

Input ¥1.5 and output ¥7.5 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥3.30, an API rate of 0.044.

How does the cache hit rate affect price?

金石API 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 金石API support?

Folkbench currently lists 24: Claude Sonnet 5, Claude Fable 5, GPT 5.6 Sol, GPT 5.6 Terra, Claude Opus 5, Kimi K3, DeepSeek V4 Pro, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, Gemini 3.8 Flash, GLM 5.3, Claude Haiku 4.5, Gemini 4 Argon, GPT-4o, GPT-4o Mini, Claude Sonnet 4.5, Claude Opus 4.5, Gemini 2.5 Flash, GPT 4.1, GPT 4.1 Mini, GPT 5 Nano, GPT 5.

What does the data security level mean?

Folkbench rates relays from 0 to 4 based on public policies and verifiable evidence; 金石API 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.