CheapRouterAuthenticity, speed and price analysis

ModelCodex促销分组-不降智Data security level 0

Comparison summary

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

GPT 6.1 Terra on CheapRouter: a coding session costs ¥0.33, ranking 7 of 20 (median ¥0.44).

Authenticity

Model consistency

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

Probe agreement66.7%
Answers20 / 30
Model fingerprintGPT 6.1 Terra
ClientAPI (Chat Completions)
Share of identity-probe answers that match the same model on the reference route. It only shows how routes differ from one another. Measured 2026-11-21 23:36 UTC. See all routes
ⓘ 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 CheapRouter0 relays
No data yet
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
Codex超级稳定分组-不降智GPT 6.1 TerraNot probed yet¥0.28¥1.40Per million tokens
Codex稳定分组-不降智GPT 6.1 TerraNot probed yet¥0.23¥1.15Per million tokens
GPT官Key分组GPT 6.1 TerraNot probed yet¥0.50¥2.50Per million tokens
Codex促销分组-不降智GPT 6.1 TerraNot probed yet¥0.15¥0.75Per million tokens

Cost per coding session

GPT 6.1 Terra · 2M input and 40k output tokens (¥) · split by token type · lower is better

20 relays
OutputInput
ⓘ USD prices are converted at 1 USD = 6.7128 CNY

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
95%
Cache hit ¥0.0075 · input ¥0.15 (per 1M tokens)
Measured hit rate
25%
Peer average 7% · 3 relays
Latest 2 rounds · 1 of 4 warm requests read the cache
Session cost at 80% hit rate
¥0.10
¥0.33 without cache, 69% saved

Cache-weighted session cost

GPT 6.1 Terra · 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 7 / 20
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 CheapRouter0 relays
No data yet

Status of each model, last 24 hours

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

No data for CheapRouter
ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
Grok 4.6Grok Ultra———
GPT 5.6 TerraCodex促销分组-不降智———
GLM 5.3国模按量付费分组———
Claude Opus 5Claude促销分组———
GPT 6.2 SolCodex促销分组-不降智———
GPT 6.2 AstraCodex促销分组-不降智———
Claude Fable 5.2Claude促销分组———
Claude Sonnet 5.5Claude促销分组———
Kimi K3.1 Pro国模按量付费分组———
GPT 6.1 TerraCodex促销分组-不降智———
Gemini 4 CarbonGemini Vertex———
Gemini 4 HydrogenGemini Vertex———
Gemini 4 ArgonGemini Vertex———
GPT 6 SolCodex促销分组-不降智———
Kimi K3国模按量付费分组———
Claude Fable 5Claude促销分组———
Claude Sonnet 5Claude促销分组———
GPT 5.6 SolCodex促销分组-不降智———
Claude Opus 4.6Claude促销分组———
GLM 5.3 Flash国模按量付费分组———
Claude Opus 4.8Claude促销分组———
Claude Opus 4.7Claude促销分组———
Claude Sonnet 4.6Claude促销分组———
Grok 4.5Grok Ultra———

About the site

A low-cost, pay-as-you-go gateway for authentic models, with transparent multipliers for Claude, Codex, Gemini, Grok and Chinese models. Offers multi-channel load balancing, ongoing model fingerprint checks and its own Agent client. Register through FolkBench for US$3 in credits.

Service details

  • Minimum top-up¥10
  • Sign-up bonusNot provided
  • Support responseWithin 4 hours on working days
  • Payment methodsAlipay, WeChat Pay, Bank card, USDT, Other
  • China invoiceSupported
  • International invoiceNot supported
  • RefundsConditional
  • PromotionsNone

FAQ

How much does GPT 6.1 Terra cost on CheapRouter?

Input ¥0.15 and output ¥0.75 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥0.33, an API rate of 0.022.

How does the cache hit rate affect price?

On CheapRouter, the cache-hit price is 5% of the input price. At an 80% hit rate a coding session costs about ¥0.10, versus about ¥0.33 without cache.Measured hit rates will replace this assumption once available.

Which models does CheapRouter support?

Folkbench currently lists 24: GPT 6 Sol, GPT 6.2 Sol, Claude Sonnet 5.5, GPT 6.2 Astra, Claude Fable 5.2, GPT 6.1 Terra, Claude Fable 5, GPT 5.6 Sol, GPT 5.6 Terra, Claude Opus 5, GLM 5.3 Flash, Claude Opus 4.8, Claude Sonnet 5, Kimi K3.1 Pro, Claude Opus 4.7, Grok 4.6, GLM 5.3, Kimi K3, Claude Opus 4.6, Gemini 4 Carbon, Gemini 4 Argon, Claude Sonnet 4.6, Grok 4.5, Gemini 4 Hydrogen.

What does the data security level mean?

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

Ordering follows site rules, including partnership tiers and operational weighting; some data are display samples.