CodexZH
OpenAI / SpaceXAI
Plans: ¥5.9/day gets $20, ¥59/mo gets about $240, and up to ¥960/mo gets about $4000; credit packs: ¥9.9 gets $30 same-day credit, ¥15 gets $50 same-day credit; the model page shows usage-based token pricing.
Codex proxy comparison
This page collects providers that publicly mention Codex, Codex CLI, Codex plans, or OpenAI-compatible access that may be used for Codex workflows. Before using one in daily coding work, verify the Base URL, model name, Responses API behavior, pricing rules, and support channel with a small test.
OpenAI / SpaceXAI
Plans: ¥5.9/day gets $20, ¥59/mo gets about $240, and up to ¥960/mo gets about $4000; credit packs: ¥9.9 gets $30 same-day credit, ¥15 gets $50 same-day credit; the model page shows usage-based token pricing.

OpenAI
Public lifetime credit packs: ¥15 for $50, ¥28 for $100, ¥81 for $300, ¥260 for $1000, ¥1250 for $5000, and ¥2400 for $10000. Model pricing is usage-based per $/1M tokens. Balance top-up has a ¥1 minimum, with Alipay and WeChat Pay shown on the recharge page.
Anthropic / OpenAI / Google
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.

Anthropic / OpenAI
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.

Anthropic / OpenAI / Google
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.
Anthropic / OpenAI / SpaceXAI
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.

Anthropic / OpenAI / Google
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.

OpenAI
The public pricing page shows billing by token consumption. Monthly plans grant fixed credits, and actual usage is deducted by model token prices; Starter $4.99/mo includes $20 credit, Basic $9.99/mo includes $60, Pro $19.99/mo includes $200, and Ultra $49.99/mo includes $600 with a $40 daily soft limit. Wallet PAYG top-ups: top up $5, top up $20 and get $10 bonus, top up $50 and get $30 bonus, top up $100 and get $70 bonus; balance remains valid long term.

Anthropic / OpenAI / Google / SpaceXAI
Top-ups credit the account at ¥1 = $1 platform credit and the balance never expires. Actual usage cost depends on the group multiplier: the screenshot shows Codex Pro (Codex-only) at 0.6x and Codex Pro (external-use edition) at 0.7x. With the Codex-only channel, $1 of list-price usage deducts about $0.6 credit, or about ¥0.60 effective cost. Official prices are converted with $1 = ¥7; top-up tiers include ¥30, ¥50, ¥100, up to ¥5000.

Anthropic / OpenAI / Google / DeepSeek / SpaceXAI
Minimum top-up is $1, converted at ¥0.66 = $1 credit. Models are billed by group multipliers, including Claude Code at 5x, Codex at 0.8x, and gemini-cli at 1.5x.

Anthropic / OpenAI / Google
The OpenAI / Codex provider cards show Codex at ¥0.7 per $1 and Codex Pro at ¥0.9 per $1. Usage-based flexible credits include a new-user ¥5 for $5 tier and ¥50 for $50 and above, with credits valid until used. Subscription plans: Standard ¥399/4 weeks with $110 weekly credit, Premium ¥899/4 weeks with $260 weekly credit, Professional ¥1799/4 weeks with $530 weekly credit, and an Enterprise plan at ¥9999/4 weeks that requires contacting support.

Anthropic / OpenAI
GPT Pro is 0.28x and uses gift credit first; CCMAX is 2x and only deducts real balance. Flexible top-ups use ¥1 = $1 balance. Subscriptions: Strawberry ¥399/4 weeks with $110 weekly credit; Raspberry ¥899/4 weeks with $260 weekly credit; Blueberry ¥1799/4 weeks with $530 weekly credit.
FAQ
It is usually an AI API proxy or coding-agent service that provides a Base URL, API key, model mapping, or plan intended for Codex CLI, Codex app, or related OpenAI-compatible coding workflows.
Check whether the provider explicitly supports Codex, which Base URL path to use, whether Responses API behavior works, the exact model name, streaming and tool-call behavior, billing rules, and support channel.
No. Codex is not just a chat client. A provider can expose OpenAI-compatible chat endpoints but still fail on the API behavior, model mapping, or tool workflow Codex expects.