破晓Authenticity, speed and price analysis

Model【限时】Codex 双十一 不降智Data security level 013 samples

Comparison summary

GPT 6 Sol on 破晓: availability over the last 24 hours is 100.0%, ranking 1 of 3 relays with data (median 98.5%); time to first token is 5.01 s, ranking 3 of 3 (median 3.90 s); a coding session costs ¥0.22, ranking 2 of 23 (median ¥0.62).

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

3 relays
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
GPT-官keyGPT 6 SolNot probed yet¥0.40¥2.00Per million tokens
codex-福利分组GPT 6 SolNot probed yet¥0.16¥0.80Per million tokens
codex-企业分组GPT 6 SolNot probed yet¥0.40¥2.00Per million tokens
【限时】不降智特价分组GPT 6 SolNot probed yet¥0.18¥0.90Per million tokens
【限时】Codex 双十一 不降智GPT 6 Sol100.00%¥0.10¥0.50Per million tokens
codex-不降智分组GPT 6 SolNot probed yet¥0.22¥1.10Per million 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 discount
Not provided
Cache hit — · input ¥0.1 (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
¥0.22
¥0.22 without cache, 0% saved

Stability

Availability

Request success rate, last 24 hours · higher is better

3 relays

Status of each model, last 24 hours

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

ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
DeepSeek V4.1 FlashDS 国模之光100.0%2.09 s29
GPT 6 Sol【限时】Codex 双十一 不降智100.0%5.01 s13
GPT 6 Astra【限时】Codex 双十一 不降智96.5%16.05 s29
GPT 5.6 TerraGPT-官key———
Claude Opus 5kiro———
DeepSeek V4 Flash 0731DS 国模之光———
DeepSeek V4 Pro 0813DS 国模之光———
Claude Haiku 4.5Claude max 满血———
Claude Fable 5Cursor———
Claude Opus 4.8kiro———
Claude Sonnet 5kiro———
GPT 5.6 Sol【限时】Codex 双十一 不降智———
Claude Opus 4.7kiro———
Claude Opus 4.6kiro———
Claude Sonnet 4.6kiro———
Claude Sonnet 4.5Claude max 满血———
Claude Opus 4.5Claude max 满血———

About the site

充值1:1 倍率稳定不变动 。每日签到、连续签到奖励、消费抽奖和福利兑换

Service details

  • Minimum top-up¥10
  • Sign-up bonusNot provided
  • Support responseNot provided
  • Payment methodsAlipay, WeChat Pay
  • China invoiceSupported
  • International invoiceNot verified
  • RefundsSupported
  • PromotionsNot provided

FAQ

How much does GPT 6 Sol cost on 破晓?

Input ¥0.1 and output ¥0.5 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥0.22, an API rate of 0.0074.

How does the cache hit rate affect price?

破晓 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 破晓 support?

Folkbench currently lists 17: GPT 6 Astra, GPT 6 Sol, DeepSeek V4.1 Flash, Claude Fable 5, Claude Opus 5, Claude Opus 4.8, GPT 5.6 Sol, GPT 5.6 Terra, Claude Sonnet 5, Claude Opus 4.7, Claude Haiku 4.5, Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0813.

What does the data security level mean?

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