FlyRouterAuthenticity, speed and price analysis

About the site

FlyRouter 是面向开发者与 AI Agent 的统一大模型网关,支持通过一个 API Key 接入 GPT、Claude、Gemini 等主流模型,并兼容 OpenAI API。平台提供透明定价、按量计费、实时用量与账单追踪,请求直达经验证的上游,不静默替换模型。同时提供开发文档、用户控制台和技术支持,帮助个人与团队更稳定、高效地将 AI 能力接入生产环境。

Service details

  • Minimum top-up$1
  • Sign-up bonus$1
  • Support response半小时内
  • Payment methodsBank card, WeChat Pay, Alipay
  • China invoiceConditional
  • International invoiceSupported
  • RefundsConditional
  • PromotionsNot provided
Modelclaude_maxData security level 0

Comparison summary

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

Claude Haiku 4.5 on FlyRouter: a coding session costs ¥3.69, ranking 1 of 2, the cheapest relay (median ¥5.50).

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 FlyRouter0 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_maxClaude Haiku 4.5Not probed yet¥1.68¥8.38Per million tokens
defaultClaude Haiku 4.5Not probed yet¥1.68¥8.38Per million tokens

Cost per coding session

Claude Haiku 4.5 · 2M input and 40k output tokens (¥) · split by token type · lower is better

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

Prices: cache hit, input and output

¥ / 1M tokens

Cache hitInputOutput
¥0¥2¥4¥6¥8¥10¥12¥14¥8.38FlyRouter金石API

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 ¥1.675 (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
¥3.69
¥3.69 without cache, 0% saved

Cache-weighted session cost

Claude Haiku 4.5 · 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 / 2
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 FlyRouter0 relays
No data yet

Status of each model, last 24 hours

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

No data for FlyRouter
ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
Claude Haiku 4.5claude_max———
GPT 5.6 Lunaclaude_max———
Gemini 4 Argondefault———
Hy 3default———
MiniMax M3default———
Claude Sonnet 5claude_max———
Kimi K3default———
GPT 5.6 Terracodex_pro———
Claude Fable 5claude_max———
GPT 5.6 Solcodex_pro———
Claude Opus 5claude_max———
Claude Opus 4.7claude_max———
Claude Opus 4.8claude_max———
Grok 4.6grok_heavy———
Claude Opus 4.6claude_max———
Claude Sonnet 4.6claude_max———
Grok 4.5grok_heavy———
GLM 5.3 Flashdefault———

FAQ

How much does Claude Haiku 4.5 cost on FlyRouter?

Input ¥1.675 and output ¥8.375 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥3.69, an API rate of 0.25.

How does the cache hit rate affect price?

FlyRouter 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 FlyRouter support?

Folkbench currently lists 18: Claude Sonnet 5, Claude Fable 5, GPT 5.6 Sol, GPT 5.6 Terra, Claude Opus 5, Kimi K3, Claude Opus 4.8, Grok 4.6, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, Grok 4.5, Claude Haiku 4.5, GPT 5.6 Luna, Gemini 4 Argon, GLM 5.3 Flash, Hy 3, MiniMax M3.

What does the data security level mean?

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