Claude API Proxy Providers

Public model pricing is shown per million tokens. Examples include gpt-5.4-mini at ¥0.1950 input / ¥0.8325 output, gpt-5.3-codex at ¥0.3300 input / ¥3.3000 output, claude-sonnet-4-6 at ¥0.8580 input / ¥3.9600 output, and gemini-3.1-pro at ¥1.5400 input / ¥9.2400 output. The only currently confirmed site-credit plans are the ¥6.8 trial plan and the ¥66 site all-access plan; the lowest effective rate comes from the small ¥6.8 trial plan and does not represent one flat unit price across all plans.

Supports both usage-based top-ups and subscription cards: usage-based top-up currently uses ¥1 = $6.75 credit, about ¥0.148 per $1 credit; subscription cards cover daily, weekly, and monthly plans. The user confirmed monthly plan prices are in CNY and limits are USD credits. Monthly Card 2 costs ¥169.99 / 30 days for a $2400 monthly limit, about ¥0.071 per $1 monthly credit, usable for Claude, Gemini, and Imagen.

Top-ups are recorded as ¥1 = $1 platform balance, with a ¥5 minimum top-up. Billing uses channel multipliers: 0.15x / 0.25x / 0.3x for Codex channels and 0.32x / 0.45x / 1.4x / 1.5x / 2.3x for Claude channels. Using the lowest Codex 0.15x channel, about ¥0.15 equals $1 credit-equivalent; actual billing follows the platform display.

Top-ups are settled at ¥1 = $1 credit, with a ¥5 minimum. Model usage is charged by group multipliers or fixed prices. The comparable cost is recorded from the gpt group, mainly Pro accounts, at 0.2x, or about ¥0.20 per $1 list-price usage. Stable groups recorded here include: gpt 0.2x, gpt-enterprise 0.6x, gpt-azure 1.2x, gpt-image 0.1x; cx2cc 0.2x; gemini 0.3x, gemini-t3 1.8x; claude 0.4x, claude-anti 0.3x, claude-copilot 0.5x, claude-free 0.25x, claude-pro 1.2x, claude-ai / claude-api 3x, claude-aws-platform 2.2x, claude-max 1.8x, claude-max-any-client 1.6x, claude-kiro 0.45x, and claude-windsurf 0.35x. Limited-time, special-price, discount, sale, and out-of-stock-prone groups are excluded.

Usage cards do not expire; the purchase page shows 100M credits for ¥35, 500M for ¥135, 1B for ¥265, and 2B for ¥468. Different model/channel conversion ranges are shown: official CC full-power ¥0.98-2.8 = $1, Turbo ¥1.3-3.5 = $1, Super special CC ¥0.492-1.4 = $1, Ultra special CC ¥0.246-0.7 = $1, Codex channel CC ¥0.123-0.35 = $1, AWS special CC ¥0.03-0.087 = $1, Gemini official ¥0.123-0.35 = $1, Codex full-power official ¥0.123-0.35 = $1, and GPT-Image official ¥0.05-0.07 per image.

CDK/redeem-code top-up uses ¥1 = $1 credit, with a ¥10 minimum top-up and usage-based token billing. The lowest visible group is CC-Kiro at 0.25x, so $1 of list-price usage deducts about $0.25 credit, or about ¥0.25 effective cost. Other visible multipliers include Codex 0.3x, GPTImage2 1x, and GPTImage2-4K 1.25x.

Top-up uses ¥1 = $1 platform balance, with a ¥20 minimum. Actual billing equals the model's official USD price multiplied by the group multiplier. The FAQ explains that lower multipliers mean lower usage cost, and the screenshot shows a 0.3x Codex special group.

Usage-based billing; Anthropic shows 0.4x / 3.6x model prices, OpenAI shows 0.7x / 1.4x / 7.2x model prices, and Google shows Gemini 2.5 / 3 / 3.1 series. Minimum top-up is ¥50. From June, new personal payments only support overseas invoices, while mainland China tax invoices require corporate public-account payment. Supports WeChat, Alipay, Visa, Mastercard, Apple Pay, and Cash App Pay.

PAYGO: ¥1 ≈ $1 site credit (pricing tiers from ¥20 to ¥5000 correspond to the same USD credit amount), with credits not expiring. Multiple monthly plans are shown, such as Team ¥1888/mo with $200 refreshed daily; the page marks them at about ¥0.31-¥0.44 per $1 credit. Models are billed by official $/MTok pricing. VIP tiers provide multiplier discounts by cumulative spend, up to about 0.88x.

The current featured Codex programming plans support Codex CLI/App/API access and Claude API mapping for Claude Code; plans are valid for 31 days. The lightweight trial is ¥59 for ¥800 card balance, about ¥0.517 per $1; the starter plan is ¥99 for ¥2000 card balance, about ¥0.347 per $1; the ¥198/¥396/¥792 plans provide ¥4000/¥8000/¥16000 card balance, all about ¥0.347 per $1; the enterprise exclusive plan is ¥2000 for ¥100000 card balance, with gpt-image-2, a 20x Pro account, 16 subaccounts, and an enterprise service group, about ¥0.140 per $1.

The public pricing page shows usage-based pricing in USD. Claude Haiku / Sonnet / Opus four-column prices are about $1/$5/$0.1/$1.25, $3/$15/$0.3/$3.75, and $5/$25/$0.5/$6.25 respectively. OpenAI/GPT pricing starts from gpt-5.4-mini at $0.75/$4.5/$0.075, while gpt-5.4 is $2.5/$15/$0.25. Wallet top-ups are settled in CNY with the current top-up exchange rate $1 = ¥1. Subscription plans show Pro $299/30 days, Max $689/30 days, Ultra $1199/30 days, and Mini $14.90/3 days; some plans may be sold out or limited to new users.

PayGO plans charge against USD credit and the balance never expires. Top-up tiers include ¥100 for $100, ¥200 for $200, ¥500 for $500, ¥1000 for $1000, and ¥5000 for $5000, so the credited balance is about ¥1 = $1. Actual usage cost depends on the provider-group multiplier: the default Codex Team/Plus mixed PayGO pool is 0.4x, so $1 of list-price usage deducts about $0.4 credit, or about ¥0.4 effective cost; the pure Pro pool is 1.2x. Claude monthly plans include ¥249/mo, ¥498/mo, ¥1000/mo, and ¥2000/mo tiers with daily and weekly quota resets. Overseas Invoice support only.