API PRICES

OpenAI · gpt-5.2-codex

Per-request prices, cheapest first

Browse all models

Price ranges per million tokens

Inference provider cash prices · Lowest 4.8125 · median 4.8125 · highest 4.8125 · 1 quotes USD / per million tokens

USD_CREDIT · Lowest 1.44375 · median 4.8125 · highest 48.125 · 191 quotes USD / per million tokens, site credit

CNY_CREDIT · Lowest 1.078 · median 9.8175 · highest 58.0646075625 · 23 quotes CNY / per million tokens, site credit

Ranked by price per request.

Search modelsModel529 matches; choose and submit to view prices.

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

Find a provider by name or address

Searching…

Browse all providers

sites have comparable prices79137 sites list this model; approximately 1 operators on this board

Lowest price per request0.24USD credits / request

Median of each provider’s lowest price0.24USD credits / request

#	Provider	Plan / conditions	Per request ↑USD credits / request	Details
Recent price
01	api.2000.runAsk or discussCollected: 16 Oct 2026, 07:38 UTC Collected this cycle View 3 plans 1 more site of the same company api.chaiquan.cc Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	default If there are no special needs, please choose this channel. If speed slows down, you can switch to the emergency special group [machine translation]Original: 如无特殊需求，请选择此渠道。如果速度变慢，可以换应急特殊分组 Operator pending verification	0.24	Full prices and sources
01	api.2000.runAsk or discussCollected: 16 Oct 2026, 07:38 UTC Collected this cycle View 3 plans 1 more site of the same company api.chaiquan.cc Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	no-limit Unrestricted group, do not select unless necessary [machine translation]Original: 无限制分组，非必要请勿选择 Operator pending verification	0.24	Full prices and sources
01	api.chaiquan.ccAsk or discussCollected: 16 Oct 2026, 07:39 UTC Collected this cycle View 3 plans 1 more site of the same company api.2000.run · main site Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	default If there are no special needs, please choose this channel. If speed slows down, you can switch to the emergency special group [machine translation]Original: 如无特殊需求，请选择此渠道。如果速度变慢，可以换应急特殊分组 Operator pending verification	0.24	Full prices and sources
01	api.chaiquan.ccAsk or discussCollected: 16 Oct 2026, 07:39 UTC Collected this cycle View 3 plans 1 more site of the same company api.2000.run · main site Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	no-limit Unrestricted group, do not select unless necessary [machine translation]Original: 无限制分组，非必要请勿选择 Operator pending verification	0.24	Full prices and sources
05	api.2000.runAsk or discussCollected: 16 Oct 2026, 07:38 UTC Collected this cycle View 3 plans 1 more site of the same company api.chaiquan.cc Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Emergency special group [machine translation]Group on site: 应急特殊分组 Special group during official restrictions, for emergency use, very fast, use recommended [machine translation]Original: 官方限制期间特殊分组，应急用，速度非常快，建议使用 Operator pending verification	0.28	Full prices and sources
05	api.chaiquan.ccAsk or discussCollected: 16 Oct 2026, 07:39 UTC Collected this cycle View 3 plans 1 more site of the same company api.2000.run · main site Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Emergency special group [machine translation]Group on site: 应急特殊分组 Special group during official restrictions, for emergency use, very fast, use recommended [machine translation]Original: 官方限制期间特殊分组，应急用，速度非常快，建议使用 Operator pending verification	0.28	Full prices and sources

Special groups · 4 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.

deprecated or disabled: 2 rows
test or debug group: 2 rows

api.2000.run · 新渠道 · gpt-5.2-codex · Per request 0.28 USD credits
api.chaiquan.cc · 新渠道 · gpt-5.2-codex · Per request 0.28 USD credits
api.2000.run · 测试渠道 · gpt-5.2-codex · Per request 0.4 USD credits
api.chaiquan.cc · 测试渠道 · gpt-5.2-codex · Per request 0.4 USD credits

View all 4 rows →

How this ranking works

All per-request prices: 21,074 prices from 649 sites (about 565 companies). 19,415 are ranked, from 634 sites (about 551 companies); 1,659 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 27 per-request prices; 10 can be compared directly (6 ranked, 4 listed separately). Not comparable yet: price not parsed yet 16, display unit not confirmed 1

6 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 values are separately unverified, without proof of free eligibility.

Per-request price = model price × group ratio, converted to site credits with the site’s own unit. Prices per second or per image are listed separately.

Prices are converted to site credits using each site’s published ratio and display multiplier. What you actually pay depends on its top-up rate. 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.

Full methodology →

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for OpenAI · gpt-5.2-codex?

llms.best, group "Codex", 1.444 USD credit per million total tokens, observed 2026-10-16. 79 sites have comparable prices.

How do I use OpenAI · gpt-5.2-codex in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-5.2-codex API to Claude Code for me". Install Skill →