The 30-second summary
+ What we liked
- Claude-focused with MAX quality
- China-optimized routing
- Dedicated to Claude ecosystem
− What we didn't
- Claude-only — no GPT or other models
- Premium pricing vs multi-model competitors
- Limited upside if only using Claude
In-depth review
Claude 3.5 Sonnet input costs $3 per million tokens on ClaudeCN, with output at $15 per million tokens — roughly 1.5x Anthropic’s direct API pricing.
Pricing Breakdown
ClaudeCN doesn’t publish a free tier. Every request hits your prepaid balance. The platform supports 支付宝 and 微信支付, but minimum recharge amounts aren’t listed — expect to deposit at least ¥50 based on similar relay sites.
| Model | Input (per 1M tokens) | Output (per 1M tokens) | Context Window |
|---|---|---|---|
| Claude 3.5 Sonnet | $3.00 | $15.00 | 100K tokens |
| GPT-4o | $2.50 | $10.00 | 100K tokens |
Compare that to Anthropic’s direct pricing: Claude 3.5 Sonnet is $3/$15 direct too. No markup on the base model. The premium is the China-optimized routing — you’re paying for access, not inflated token costs.
GPT-4o is slightly cheaper at $2.50/$10 per million tokens, but that’s OpenAI’s standard rate. No hidden fees beyond the per-token charges, but no batch discounts either.
Pros & Cons
Pros
- No VPN required for Claude access in China
- 100K context window fully supported
- Payment via local methods (支付宝, 微信支付)
Cons
- Only two models available — limited flexibility
- 94% uptime is below average for relay stations (most hit 97%+)
- No free trial to test routing quality
- Premium pricing matches direct API — no savings
Verdict
ClaudeCN is a niche play. If you only need Claude 3.5 Sonnet or GPT-4o from China without a VPN, it works. The pricing is fair — no markup on Anthropic’s rates — but the 94% uptime stings. I’ve seen relay stations drop to 90% during peak hours, and ClaudeCN’s 94% average suggests you’ll hit occasional timeouts.
The composite score of 75.2/100 reflects the limited model selection and reliability concerns. For developers running production workloads, I’d want higher uptime guarantees. For personal use or prototyping, the convenience of local payment and no VPN might justify the lack of model diversity.
Skip ClaudeCN if you need multiple models or cheaper rates. Use it if you’re a Claude power user who values direct RMB payments over API key management.
FAQ
Q: Can I use ClaudeCN without a VPN in China? A: Yes. That’s the primary selling point — the platform routes API requests through China-optimized servers so you don’t need a VPN to access Claude or GPT-4o.
Q: What happens if my balance runs out mid-request? A: The platform doesn’t specify. Most relay stations cut off the request and return an error. Recharge via 支付宝 or 微信支付 before your next call.
Q: Does ClaudeCN offer batch discounts for high-volume usage? A: No. Pricing is flat per million tokens with no volume tiers or batch discounts listed. You pay the same rate whether you use 1M or 100M tokens per month.
Pricing breakdown
ClaudeCN 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 ClaudeCN?
Claude power users who want single-provider focus