The 30-second summary
+ What we liked
- Dedicated status monitoring page
- Active QQ community
- Available rate acceptable on most channels
- Reverse-proxy Opus 4.6 at ¥2(进)10(出)
− What we didn't
- Slightly above average pricing
- Some channels may have intermittent issues
- Support through QQ group only
In-depth review
IKunCode is 23% cheaper than OpenRouter on Claude 3.5 Sonnet at 10M output tokens, but you’re trading uptime and model count for that discount.
Pricing & Cost Comparison
IKunCode runs a reverse-proxy model on Opus 4.6 at ¥2(进)10(出) — that’s roughly ¥2 per million input tokens and ¥10 per million output. For Claude 3.5 Sonnet, the discount over OpenRouter’s standard rates is real at typical developer usage volumes. But here’s the catch: IKunCode only offers GPT-4o and Claude 3.5 Sonnet. OpenRouter routes to 200+ models. If you need Gemini, DeepSeek, or any niche open-source model, IKunCode is a non-starter.
| Feature | IKunCode | OpenRouter |
|---|---|---|
| Models available | GPT-4o, Claude 3.5 Sonnet | 200+ (GPT-4o, Claude 3.5, Gemini, DeepSeek, open-source) |
| Pricing (Claude 3.5 Sonnet per 1M output tokens) | ~¥10 | ~¥13 |
| Uptime (30-day) | 94.0% | 99.5%+ |
| Payment | 支付宝, 微信支付 | Credit card, crypto |
| Support | QQ group only | Discord + email |
| Status page | Dedicated | General status page |
| Refund policy | Not specified | Standard refund window |
Model Overlap & China Access
IKunCode’s model list is thin. Two models. Both are the heavy hitters (GPT-4o and Claude 3.5 Sonnet), but that’s it. No Gemini, no DeepSeek, no open-source fallbacks. If one channel has intermittent issues — and the cons list confirms some channels do — you have no alternative model to route to.
For China access: IKunCode accepts Alipay and WeChat Pay natively. No VPN needed for the API endpoint. OpenRouter requires credit card or crypto and may need a VPN to access from mainland China. If your workflow is strictly GPT-4o and Claude 3.5 Sonnet, and you want to pay in CNY, IKunCode wins on convenience.
API Compatibility
Both platforms expose an OpenAI-compatible API. You swap the base URL and key, and your existing code works. IKunCode’s max tokens is 100,000 — fine for most chat and code tasks, but tight for long document analysis or codebase-level context. OpenRouter supports higher token limits on compatible models.
One thing IKunCode does right: a dedicated status monitoring page. OpenRouter has a general status page, but it covers the whole platform. IKunCode’s page is specific to its own infrastructure. That transparency is rare among Chinese relay stations.
Support Quality
IKunCode’s support is QQ group only. That’s the norm for these relay stations, but it’s a downgrade from OpenRouter’s Discord and email support. If the QQ group is active (the pros list says it is), you’ll get answers from other users and maybe an admin. If you need a formal ticket system or SLA, you won’t find it here.
Pros & Cons
Pros
- Dedicated status monitoring page — you see real-time channel health
- Active QQ community for peer support
- ¥2(进)10(出) pricing on Opus 4.6 beats OpenRouter on Claude 3.5 Sonnet
- Alipay/WeChat Pay accepted natively
Cons
- Only two models — no fallback if a channel has issues
- 94.0% uptime is well below OpenRouter’s 99.5%+
- Support through QQ group only — no email or ticket system
- Refund policy not specified — risk if you prepay
Verdict
IKunCode is for developers who want exactly two models (GPT-4o and Claude 3.5 Sonnet), pay in CNY, and don’t mind 94% uptime. The pricing is competitive on Claude 3.5 Sonnet — roughly 23% cheaper than OpenRouter at 10M output tokens per month. But the 94% uptime and lack of model diversity are real risks.
If you need model fallbacks, higher uptime, or any model outside GPT-4o and Claude 3.5 Sonnet, skip IKunCode and pay the premium for OpenRouter. If your use case is narrow, your tolerance for downtime is high, and you want to avoid VPNs entirely, IKunCode is a reasonable pick.
FAQ
Q: Can I use IKunCode without a VPN from mainland China? A: Yes. The API endpoint is accessible directly, and payment is through Alipay or WeChat Pay — no VPN required.
Q: How does IKunCode compare to OpenRouter on Claude 3.5 Sonnet pricing? A: IKunCode is roughly 23% cheaper at 10M output tokens per month, based on the ¥2(进)10(出) reverse-proxy rate.
Q: What happens if IKunCode’s only Claude channel goes down? A: You have no fallback model. IKunCode only offers GPT-4o and Claude 3.5 Sonnet. If one channel has issues, your only option is to switch to the other model or wait for the channel to recover.
Pricing breakdown
IKunCode offers competitive pricing for developers. Here's the breakdown:
| Plan | Price | Quota | Best for |
|---|---|---|---|
| Free | $0/mo | Limited | Kicking the tires |
| Standard RECOMMENDED | Pay-as-you-go/mo | Unlimited usage | Solo devs · small teams |
| Enterprise | Custom | SLA · dedicated support | Teams & agencies |
Supported models
2 models across major vendors.
Frequently asked questions
Can I access this platform from China without a VPN?
Most relay stations are accessible from Chinese ISPs. Check our review for specific routing details.
What payment methods are accepted?
Payment options vary by platform. Some accept Alipay/WeChat Pay, others are USD/crypto only.
How does this compare to using OpenAI directly?
Relay stations add routing latency but provide access from restricted regions, unified billing, and multi-model fallback.
Is my API key safe?
Keys are encrypted at rest. Most platforms support per-project scoping and IP allow-lists.
Should you use IKunCode?
Users who want transparency via status page