Basic
¥79 /mo
- •Daily limit: $30
- •Weekly limit: $100
- •Monthly limit: $360
- •For solo developers and light-to-mid Codex workflows
- •Includes mainstream Codex models and baseline support
CodeProxy CLI SessionLive
$codeproxyrequest --model gpt-5.6-sol
payload:{ "message": "Hello!" }
routeupstream=OpenAI latency=183ms
200tokens=128 cost=$0.0021
$
Deep Codex Compatibility
Optimized for OpenClaw and Codex-heavy workflows while keeping official API habits and developer experience.
Stable Availability
Multi-account pooling and smart failover reduce rate-limit interruptions for long-running heavy usage.
High-Quota Subscriptions
Large-capacity Codex plans designed for high concurrency and long coding sessions.
Better Than Official Pricing
Fine-grained routing and resource scheduling deliver better-value Codex pricing for sustained use.
Developer-Focused Low Latency
Connection pooling and request-path optimization keep coding, debugging, and iteration smooth.
Subscription & Cost Visibility
Track request volume, latency, quota, and cost in real time for tighter team control.
Enterprise Partnership
Built for business customers with corporate bank transfers, invoices, and formal contracts.
Popular Agent Tools
Works with Claude Code, Codex CLI, Cursor, OpenCode, Cline, and other popular agent tools.
Complete Docs & Fast Support
Clear integration guides and examples, backed by responsive customer support that resolves issues quickly.
Transparent pricing
Comparison of Mainstream Model CodeProxy vs. Official Pricing
Compare the same models and unit so the savings are easy to understand.
| Model | CodeProxy Input / output (CNY) | Official reference (USD) | Official in CNY | Estimated saving |
|---|
Unit: per 1M tokens (input / output); reference rate: 1 USD = 7.2 CNY.
Official price updated: 2026/8/5. Final billing reflects current prices and exchange rates.
Pricing
Built for heavy OpenClaw and Codex usage, with stable high-quota plans at better value.
Product-specific subscription tiers
The subscription area is now split into Codex, Claude Code, and Grok Search. Codex and Claude Code have separate pricing ladders, while Grok Search keeps its fixed package.
Per-product pricing | Clearer limits
Built for everyday coding throughput
Codex Plans
Codex plans focus on better price-performance and roomier limits for solo builders, small teams, and sustained engineering output.
More cost-efficient
Entry
Standard
Best-value Codex tier
¥199 /mo
- •Daily limit: $60
- •Weekly limit: $300
- •Monthly limit: $1200
- •For stable high-frequency development and small-team collaboration
- •Includes latest Codex models and priority support
Ultra
¥399 /mo
- •Daily limit: $140
- •Weekly limit: $700
- •Monthly limit: $2800
- •For heavy agent coding, parallel projects, and sprint periods
- •Built for higher-frequency usage and dedicated support
Higher model cost, tighter quota design
Claude Code Plans
Claude Code costs materially more than Codex, so its pricing and limits are designed separately for teams that truly need longer-context agent workflows.
Higher-cost tiering
Basic
¥249 /mo
- •Daily limit: $30
- •Weekly limit: $150
- •Monthly limit: $500
- •For solo developers using Claude Code steadily on long-context coding tasks
- •An entry tier that balances usability with cost control
Standard
Balanced Claude Code tier
¥599 /mo
- •Daily limit: $70
- •Weekly limit: $350
- •Monthly limit: $1400
- •For medium-to-high-frequency Claude Code workflows, reviews, and complex agent tasks
- •Better suited for sustained multi-turn sessions and primary daily use
Ultra
¥1299 /mo
- •Daily limit: $150
- •Weekly limit: $750
- •Monthly limit: $3000
- •For core team members, heavy agent workflows, and parallel project delivery
- •Best for complex multi-turn tasks, very long sessions, and higher quality expectations
Price locked, layout refreshed only
Grok Search Package
Grok Search remains a fixed 3000-call / 180-day package. This update only changes how it is presented in the page layout.
Price unchanged
Grok Search
¥50
- •CN¥50 with 180 days validity
- •3000 total search requests included
- •Price is already fixed and unchanged in this update
- •A fixed-request package rather than wallet-style real-time deduction
- •Best for lightweight retrieval workloads that need stable search quota
FAQ
Frequently asked questions and quick answers.
What models are supported?
Currently, we support OpenAI Codex models including gpt-image-2,gpt-5.6-sol,gpt-5.6-luna,gpt-5.6-terra,gpt-5.5，gpt-5.4,gpt-5.4-mini, gpt-5.3-codex, gpt-5.2-codex, gpt-5.2,claude-opus-4-6,claude-opus-4-7,claude-opus-4-8,claude-fable-5,claude-sonnet-5,claude-sonnet-4-6,claude-haiku-4-5-20251001,claude-sonnet-4-5-20250929,grok-4.3,deepseek-v4-flash,deepseek-v4-pro,kimi-k3. We will continue to add more model support in the future.
How do I get started?
Sign up and log in, create an API key in the dashboard, then use the request examples in docs.
Which tools are supported?
It works with mainstream AI coding and development tools, including Codex CLI, Codex App, Codex plugins, Claude Code, OpenCode, and OpenClaw. If a tool supports compatible API keys or OpenAI/Codex-compatible integration, it can usually be configured directly.
Do you support subscription billing and real-time charges?
Yes. We support both monthly subscriptions and pay-as-you-go billing, with live usage details shown in billing pages.
Can I upgrade or switch plans later?
Yes. You can upgrade, downgrade, or switch plans anytime with prorated settlement.
Do you support enterprise integration and cooperation?
Yes. codeproxy.dev focuses on enterprise partnerships and long-term service. We provide professional technical integration, solution assessment, and dedicated support, with corporate bank transfers, official invoices, and formal contracts available. Contact our team to discuss enterprise accounts, usage planning, and service guarantees.
What are the differences between this and the official Codex?
Experience is identical, but with clear advantages: zero account ban risk, intelligent scheduling to avoid speed limits, more usage quotas, stable quality, and exclusive official discount pricing. Dedicated technical support, Business-level model support, and fully compatible API format. A professional solution tailored for indie developers and enterprises.
How does the service performance compare to the official?
Our service provides the same performance, model quality, and data format as the official Codex. Through dynamic resource pools and load balancing strategies, we offer better stability and zero rate limiting. When one account hits a limit, it immediately switches to another to ensure uninterrupted usage.
How is after-sales support guaranteed?
We provide 7x24 technical support, ensuring quick response to your issues at any time. Whether it is integration problems, usage questions, or billing inquiries, we offer professional solutions. Our goal is to let you use Codex services worry-free and focus on Vibe Coding.
Testimonials
Feedback from real teams using CodeProxy.
"Integration was smooth. We moved our existing API flow in under an hour."
Liam
Indie Developer
"The account pool improved reliability a lot. We rarely hit rate-limit interruptions now."
Mina
AI Product Manager
"Billing details are clear and traceable by teammate, making budget control much easier."
Tao Zhang
Engineering Lead
"We used to maintain multiple keys and policies. Now everything is unified under one entry point."
Alex
Team Admin
"We saw cost improvements in the first week. Usage-based billing fits experimentation phases very well."
Kiki
Startup Founder
"Routing and billing metrics are transparent, which makes reconciliation with finance much easier."
Nan Chen
Operations Lead
Contact & Next Step
If you are evaluating integration, reach out and we can help quickly.
Ready to Get Started?
Sign up now and get free trial credits to experience seamless AI access
Sign Up Free