跪拜 Guibai
← All articles
AI Programming

A Single Monthly Credit Pool Now Feeds 11 Chinese LLMs Into Claude Code and Codex

By 一只牛博 ·
Read original on juejin.cn ↗ Google Translate ↗ Alt translation

Fragmented AI subscriptions and short-cycle rate limits are a real friction point for developers who switch models per task. A unified credit pool with a single API key removes the overhead of managing multiple accounts and quota windows, though the QPS 2 cap and tool-use restrictions mean it suits solo interactive coding, not batch automation.

Summary

Instead of juggling separate subscriptions for GLM, Kimi, DeepSeek, and MiniMax, the AiiOnly Token Plan puts all 11 models into a shared monthly Credits pool. The Standard tier costs 79 yuan/month for 6.32 million Credits, with a QPS limit of 2. Both OpenAI-compatible and Anthropic Messages endpoints are provided, though not every model supports both protocols. A new desktop client, VeryClaw, integrates model access, chat, agents, skills, and scheduled tasks into a single workbench, storing API keys locally.

A walkthrough connects the plan to Claude Code via CC Switch, mapping four role slots — Sonnet, Opus, Fable, Haiku — to DeepSeek-V4-Pro, DeepSeek-V4-Flash, GLM-5.2, and Kimi-K3. The same plan then feeds Codex through the OpenAI Chat Completions protocol, where Kimi-K3 generates a complete HTML/CSS/JS task board in one session. Both tools draw from the same monthly pool, with per-request credit consumption visible in the console.

The plan explicitly forbids use for custom application backends, automation scripts, or batch calls; it is restricted to interactive agents and programming tools. Purchases are non-refundable and cannot be downgraded.

Takeaways
Standard tier includes 6.32 million monthly Credits and a QPS limit of 2, priced at 79 yuan/month.
The plan covers 11 models across DeepSeek, GLM, Kimi, and MiniMax families, including the newly added GLM-5.3.
Both OpenAI-compatible (/v1/chat/completions) and Anthropic-compatible (/v1/messages) endpoints are available, but not every model supports both protocols.
Credits are a platform-specific unit; consumption varies by model and by input/output/cache token counts, so request counts alone do not reflect cost.
CC Switch maps Claude Code role slots to actual model IDs; the request address must use the bare endpoint (https://llm.aiionly.com) without appending /v1/messages.
Codex connects via the OpenAI Chat Completions protocol, not the Responses API, and draws from the same monthly credit pool.
The VeryClaw desktop client bundles model access, chat, agents, skills, and scheduled tasks, with API keys stored locally.
The plan is restricted to interactive agents and programming tools; custom backends, automation scripts, and batch calls are prohibited.
Purchases are non-refundable and cannot be downgraded.
Conclusions

Short-cycle quota windows — 5-hour rolling limits and weekly caps — are a bigger pain point for solo developers than raw model capability, and a monthly pool directly addresses that scheduling friction.

Mapping Claude Code's role slots to different models turns the tool into a model router: backend logic hits a reasoning-heavy model, frontend work hits a multimodal one, all without leaving the session.

The explicit ban on automation scripts and batch calls signals that the pricing is calibrated for interactive, human-paced coding, not for programmatic throughput.

VeryClaw's local API key storage and integrated tool execution point toward a desktop-agent model where the client, not a cloud service, orchestrates model calls and file operations.

Concepts & terms
Credits (AiiOnly)
A unified billing unit on the AiiOnly platform. Each model request consumes Credits based on the actual input, output, and cache tokens used, with different models having different deduction multipliers. Credits are not equivalent to raw tokens.
CC Switch
A configuration tool that intercepts Claude Code's model requests and reroutes them to alternative API endpoints and model IDs, allowing Claude Code to use non-Anthropic models through its native role-slot interface.
QPS (Queries Per Second)
The maximum number of API requests allowed per second. The Standard plan's QPS of 2 means at most two concurrent or rapid-sequential requests can be processed, making it unsuitable for high-throughput batch workloads.
Source: juejin.cn ↗ Google Translate ↗ Backup ↗