Switch model

API PRICES

codex-auto-review

Provider prices, cheapest first

Browse all models

codex-auto-review official price: not yet recorded. Cheapest relay: dragon3api.com, group "gpt special price [machine translation] (on site: gpt-特惠)" 0.675 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 329 sites have comparable prices; 329 sites list this model.Relay blended price uses 75% input and 25% output.

Price ranges per million tokens

Relay USD credit prices · Lowest 0.675 · median 1.8563 · highest 3.15 · 4 quotes USD / per million tokens, site credit

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Filtering by provider: dragon3api.com

Searching…

Browse all providers
Clear filters

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest 0.675 · median 1.8563 · highest 3.15 (4 quotes, USD credits per million total tokens)

sites have comparable prices329329 sites list this model; approximately 1 operators
Lowest input price0.3USD credits / 1M
Median of each provider’s lowest price0.3USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
01dragon3api.comAsk or discussCollected:
Collected this cycle
View 4 plans
gpt special price [machine translation]Group on site: gpt-特惠
Name on site: codex-auto-review
GPT lowest-price tier · fluctuates considerably, please report issues, don't rush [machine translation]Original: GPT 最低价档 · 波动较大,出问题请反馈,别催
Operator pending verification
0.31.80.030.675Median price ÷ this price: 2.8×Full prices and sources
02dragon3api.comAsk or discussCollected:
Collected this cycle
View 4 plans
gpt-plus
Name on site: codex-auto-review
GPT everyday tier · cheap, cache hit rate and stability not as good as pro [machine translation]Original: GPT 日常档 · 便宜,缓存命中和稳定性不如 pro
Operator pending verification
0.553.30.0551.2375Median price ÷ this price: 1.5×Full prices and sources
03dragon3api.comAsk or discussCollected:
Collected this cycle
View 4 plans
gpt-pro
Name on site: codex-auto-review
GPT main tier · cache hits, speed and stability are the best, first choice for long tasks, can be subscribed to [machine translation]Original: GPT 主力档 · 缓存命中、速度和稳定性最好,长任务首选,可订阅
Operator pending verification
1.16.60.112.475Median price ÷ this price: 0.8×Full prices and sources
04dragon3api.comAsk or discussCollected:
Collected this cycle
View 4 plans
gpt-promax
Name on site: codex-auto-review
GPT ultra-high cache tier · highest cache hit rate, saves the most on long context/long sessions, subscription available [machine translation]Original: GPT 超高缓存档 · 缓存命中率最高,长上下文/长会话最省钱,可订阅
Operator pending verification
1.48.40.143.15Median price ÷ this price: 0.6×Full prices and sources
Special groups · 20 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

  • near-zero-ratio group: 13 rows
  • top-up or membership gated: 3 rows
  • unrecognized flag USAGE_IMAGE_ONLY: 3 rows
  • ratio looks like a placeholder: 1 rows
  • ainzy.net · codex-starter · codex-auto-review · Input 0.002 / Output 0.012 USD credits / 1M
  • ai.saigou.work · grok - perk group [machine translation]Group on site: grok-福利分组 · codex-auto-review · Input 0.0025 / Output 0.00025 USD credits / 1M
  • ainzy.net · codex-plus · codex-auto-review · Input 0.004 / Output 0.024 USD credits / 1M
  • ainzy.net · codex-pro · codex-auto-review · Input 0.006 / Output 0.036 USD credits / 1M
  • api.zzswitch.com · Special price plus [machine translation]Group on site: 特惠plus · codex-auto-review · Input 0.006 / Output 0.036 USD credits / 1M
  • ainzy.net · codex-ultra · codex-auto-review · Input 0.008 / Output 0.048 USD credits / 1M
  • api-top.com · Codex perk [machine translation]Group on site: Codex福利 · codex-auto-review · Input 0.02 / Output 0.12 USD credits / 1M
  • api-top.com · GPT-Plus Enjoy [machine translation]Group on site: GPT-Plus畅享 · codex-auto-review · Input 0.04 / Output 0.24 USD credits / 1M
  • api-top.com · GPT-Pro perk [machine translation]Group on site: GPT-Pro福利 · codex-auto-review · Input 0.06 / Output 0.36 USD credits / 1M
  • nty-hk.zhouyang168.top · Codex11 · codex-auto-review · Input 0.075 / Output 0.6 USD credits / 1M
View all 20 rows →
How this ranking works

All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 1910 recorded prices; 1026 can be compared directly (996 ranked, 30 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 352, price not parsed yet 283, display unit not confirmed 89, ratio looks unset 83, billed per request or another unit 31, scope of the official doc price not confirmed 4

4 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for codex-auto-review?

dragon3api.com, group "gpt-特惠 (gpt special price)", 0.675 USD credit per million total tokens, observed 2026-10-16. 329 sites have comparable prices.

How do I use codex-auto-review in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest codex-auto-review API to Claude Code for me". Install Skill →