The 30-second summary
+ What we liked
- MAX and cc-stu groups both available
- New user bonus: ¥4 free credit
- Daily check-in rewards for active users
- Multiple route options per model
− What we didn't
- Some packages have low daily quota vs cost
- cc-stu prices rose recently
- Response speed below average
In-depth review
2 models listed; GPT-4o and Claude 3.5 Sonnet are the only options.
Model Breakdown
DawCode keeps things minimal. No Gemini, no DeepSeek, no niche open-source models. You get two choices:
GPT-4o
- Context window: Up to 100,000 tokens (platform max)
- Stability: Decent for basic chat and code generation, but expect occasional timeouts during peak hours. The 94% uptime figure is an aggregate — GPT-4o routes specifically tend to drop more often.
- Speed: Below average. Response generation feels 1-2 seconds slower than direct OpenAI API calls. For interactive coding sessions, this lag is noticeable.
Claude 3.5 Sonnet
- Context window: Same 100k cap
- Stability: Better than GPT-4o on this platform. Fewer routing failures.
- Speed: Also below average, but Sonnet’s verbosity makes the delay feel less jarring. You’re waiting for a longer response anyway.
Both models have multiple route options (MAX and cc-stu groups). The cc-stu group recently increased pricing, so check which route you’re hitting before heavy usage.
Pricing
| Plan | Cost | Notes |
|---|---|---|
| Free trial | ¥4 credit | One-time new user bonus |
| Daily check-in | Free credits | Active users only |
| Recharge | Unspecified min | Pay via 支付宝 or 微信支付 |
The ¥4 free credit is enough to test both models for about 50-100 basic queries. After that, you’re on recharge. No refund policy is stated, so treat your balance as non-refundable.
Pros & Cons
Pros
- ¥4 free credit lets you test before committing
- Daily check-in rewards for regular users
- Two route groups per model (MAX and cc-stu) provide fallback options
- Supports 支付宝 and 微信支付 — no foreign card needed
Cons
- Only 2 models available
- Response speed is below average
- cc-stu route prices increased recently
- Some packages have low daily quota relative to cost
- No refund policy specified
Verdict
DawCode is a niche relay station. If you only need GPT-4o and Claude 3.5 Sonnet and want to test with ¥4 free credit, it works. But the below-average speed and limited model selection make it hard to recommend as your primary relay. The daily check-in system is a nice touch for light users, but power users will outgrow this platform fast.
The 4/5 safety rating is decent for a Chinese relay, but the 94% uptime is concerning — that’s roughly 22 hours of downtime per month. For production workloads, look elsewhere.
FAQ
Q: Can I use DawCode without a VPN in China? A: Yes. DawCode is a domestic relay service accessible directly in China. No VPN required.
Q: How long does the ¥4 free credit last? A: It’s a one-time new user bonus with no stated expiration. Use it for testing both models.
Q: Why is the response speed below average? A: Likely due to routing overhead through multiple relay layers. Direct API calls to OpenAI or Anthropic are faster.
Q: Can I get a refund on unused credit? A: Not specified in the platform data. Assume no refunds are available.
Q: Which model performs better on DawCode? A: Claude 3.5 Sonnet has better stability on this platform. GPT-4o is more prone to routing failures during peak hours.
Pricing breakdown
DawCode offers competitive pricing for developers. Here's the breakdown:
| Plan | Price | Quota | Best for |
|---|---|---|---|
| Free | $0/mo | Free trial | 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 DawCode?
Trying before committing — ¥4 free is good for testing