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
(seconds)
coding session
availability
Comparison summary
Kimi K3 on FlyRouter: a coding session costs ¥11.1, ranking 3 of 4 (median ¥11.1).
Authenticity
Model consistency
Output distribution for the same requests on this relay and on the official API · higher is better
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
Price
Groups and models
| Group | Model | Availability | Input price | Output price | Pricing unit |
|---|---|---|---|---|---|
| default | Kimi K3 | Not probed yet | ¥5.03 | ¥25.13 | Per million tokens |
Cost per coding session
Kimi K3 · 2M input and 40k output tokens (¥) · split by token type · lower is better
Prices: cache hit, input and output
¥ / 1M tokens
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-weighted session cost
Kimi K3 · 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
Stability
Availability
Request success rate, last 24 hours · higher is better
Status of each model, last 24 hours
One cell per hour · green ok, yellow delayed, red failed
| Model | Group | Availability | Last 24 hours | First token | Samples |
|---|---|---|---|---|---|
| Claude Haiku 4.5 | claude_max | — | — | — | |
| Gemini 4 Argon | default | — | — | — | |
| Hy 3 | default | — | — | — | |
| MiniMax M3 | default | — | — | — | |
| GPT 5.6 Luna | claude_max | — | — | — | |
| Kimi K3 | default | — | — | — | |
| Claude Fable 5 | claude_max | — | — | — | |
| GPT 5.6 Sol | codex_pro | — | — | — | |
| Claude Opus 5 | claude_max | — | — | — | |
| Claude Sonnet 5 | claude_max | — | — | — | |
| GPT 5.6 Terra | codex_pro | — | — | — | |
| Claude Opus 4.8 | claude_max | — | — | — | |
| Grok 4.6 | grok_heavy | — | — | — | |
| Claude Opus 4.6 | claude_max | — | — | — | |
| Claude Sonnet 4.6 | claude_max | — | — | — | |
| Claude Opus 4.7 | claude_max | — | — | — | |
| Grok 4.5 | grok_heavy | — | — | — | |
| GLM 5.3 Flash | default | — | — | — |
FAQ
How much does Kimi K3 cost on FlyRouter?
Input ¥5.025 and output ¥25.125 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥11.1, 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 Fable 5, GPT 5.6 Sol, Claude Sonnet 5, Claude Opus 5, GPT 5.6 Terra, Kimi K3, Claude Opus 4.8, Grok 4.6, Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.7, Grok 4.5, Claude Haiku 4.5, Gemini 4 Argon, GPT 5.6 Luna, 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.