IKunCodeAuthenticity, speed and price analysis

About the site

IKunCode has operated steadily for over 1 year, providing one-stop AI services including Claude, GPT, Gemini and leading Chinese models.

Service details

  • Minimum top-up5 CNY
  • Sign-up bonus0
  • Support responseContact customer service in advance for invoicing
  • Payment methodsAlipay, WeChat Pay
  • China invoiceSupported
  • International invoiceNot verified
  • RefundsSupported
  • PromotionsTop up 500 or more to access an exclusive pricing multiplier

Strengths

  • Established after-sales support groups and responsive customer service.

Limitations

  • A wider selection of pricing groups would be useful.
ModelCodex-ProData security level 048 samples

Comparison summary

GPT 6 Astra on IKunCode: availability over the last 24 hours is 100.0%, ranking 1 of 4 relays with data (median 100.0%); time to first token is 4.67 s, ranking 2 of 4 (median 5.28 s); a coding session costs ¥15.4, ranking 8 of 9 (median ¥2.20).

Authenticity

Model consistency

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

Probe agreement70.0%
Answers21 / 30
Model fingerprintGPT 6 Sol
ClientAPI (Chat Completions)

gpt-6.1-sol (also known as astra-minor) is essentially gpt-6-astra with a shallower reasoning loop; they share the same base model, so model fingerprinting cannot distinguish them.

Share of identity-probe answers that match the same model on the reference route. It only shows how routes differ from one another. Measured 2026-11-18 21:17 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

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

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
Codex-ProGPT 6 Astra100.00%¥7.00¥35.00Per million tokens
CodexGPT 6 AstraNot probed yet¥2.50¥12.50Per million tokens
Codex-MixedGPT 6 AstraNot probed yet¥5.00¥25.00Per million tokens

Cost per coding session

GPT 6 Astra · 2M input and 40k output tokens (¥) · split by token type · lower is better

9 relays
OutputInput
ⓘ USD prices are converted at 1 USD = 6.7128 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
90%
Cache hit ¥0.7 · input ¥7 (per 1M tokens)
Measured hit rate
0%
Peer average 13% · 6 relays
Latest 2 rounds · 0 of 2 warm requests read the cache
Session cost at 80% hit rate
¥5.32
¥15.4 without cache, 65% saved

Cache-weighted session cost

GPT 6 Astra · 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 8 / 9
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

4 relays

Status of each model, last 24 hours

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

ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
GPT 6 AstraCodex-Pro100.0%4.67 s48
Claude Opus 5.5cc-kiro100.0%3.16 s48
Claude Opus 5cc-kiro100.0%2.54 s48
Claude Sonnet 5cc-kiro100.0%8.14 s48
Grok 4.6grok-heavy-test100.0%5.91 s48
Grok 4.5grok-heavy-test100.0%2.32 s18
Grok 4.7grok-heavy-test95.8%3.78 s48
DeepSeek V4.1 Flashdeepseek-cheap91.2%5.75 s34
GPT 6.1 SolCodex———
DeepSeek V4 Flash Vision Expdeepseek-official———
GLM 5.2glm-official———
Gemini 4 Argongemini———
DeepSeek V4 Flashdeepseek-official———
Kimi K3kimi———
DeepSeek V4 Prodeepseek-cheap———
Claude Opus 4.8cc-kiro———
Claude Fable 5cc逆向3———
GLM 5.3 Flashglm-official———
GPT 5.6 SolCodex-Pro———
GLM 5.3glm-official———
GPT 5.6 TerraCodex-Pro———
Claude Opus 4.7cc-kiro———
Claude Sonnet 4.6cc-kiro———
Claude Opus 4.6cc-kiro———
Gemini 3.8 Flashgemini———

FAQ

How much does GPT 6 Astra cost on IKunCode?

Input ¥7 and output ¥35 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥15.4, an API rate of 0.10.

How does the cache hit rate affect price?

On IKunCode, the cache-hit price is 10% of the input price. At an 80% hit rate a coding session costs about ¥5.32, versus about ¥15.4 without cache.Measured hit rates will replace this assumption once available.

Which models does IKunCode support?

Folkbench currently lists 25: GPT 6 Astra, Claude Opus 5.5, GPT 6.1 Sol, DeepSeek V4.1 Flash, Claude Fable 5, Grok 4.7, Claude Opus 4.8, Claude Opus 5, GLM 5.3 Flash, GPT 5.6 Sol, Claude Sonnet 5, GPT 5.6 Terra, Kimi K3, GLM 5.3, Grok 4.6, Claude Opus 4.7, Gemini 3.8 Flash, Gemini 4 Argon, Claude Sonnet 4.6, Claude Opus 4.6, Grok 4.5, DeepSeek V4 Pro, GLM 5.2, DeepSeek V4 Flash, DeepSeek V4 Flash Vision Exp.

What does the data security level mean?

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