Switch model

API PRICES

OpenAI · gpt-5.6-terra

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 2 / output 12 USD/million tokensOpenAI ·
Lowest inference provider (cash)
Input 2 / output 12 USD/million tokensOpenRouter · Aggregator ·
Lowest relay (credit)
0.225 USD credit/million total tokensainzy.net "codex-enterprise" ·

Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.

OpenAI · gpt-5.6-terra official price: input 2, output 12 USD per million tokens (OpenAI, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 2, output 12 USD per million tokens. Cheapest relay: ainzy.net, group "codex-enterprise" 0.225 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 253 sites have comparable prices; 955 sites list this model.Relay blended price uses 75% input and 25% output.

Price ranges per million tokens

Official cash prices · Lowest 4.5 · median 6 · highest 7.5 · 2 quotes USD / per million tokens

Inference provider cash prices · Lowest 4.5 · median 4.5 · highest 4.5 · 1 quotes USD / per million tokens

Relay USD credit prices · Lowest 0.225 · median 2.75 · highest 49.5 · 159 quotes USD / per million tokens, site credit

Relay CNY credit prices · Lowest 0.225 · median 1.4063 · highest 38.5 · 43 quotes CNY / per million tokens, site credit

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
OpenAI2120.22.5USD / 1M tokens
Official source
OpenAI4180.45USD / 1M tokens
Official source

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.

Inference providers

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
OpenRouter · Aggregator2120.22.5USD / 1M tokens
Official source

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

Searching…

Browse all providers

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

Price range: lowest 0.225 · median 2.75 · highest 49.5 (159 quotes, USD credits per million total tokens)

sites have comparable prices253955 sites list this model; approximately 171 operators
Lowest input price0.1USD credits / 1M
Median of each provider’s lowest price1USD 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
98api.bblabu.hkAsk or discussCollected:
Collected this cycle
View 1 plans
OpenAI
x1 rate multiplier gpt plus account pool, default recommendation [machine translation]Original: x1倍率 gpt plus号池 默认推荐
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98api.clawsocket.comAsk or discussCollected:
Collected this cycle
View 1 plans
default
Default group [machine translation]Original: 默认分组
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98api.joeychen.xyzAsk or discussCollected:
Collected this cycle
View 3 plans
default
default
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98api.mixrai.comAsk or discussCollected:
Collected this cycle
View 1 plans
default
Default group [machine translation]Original: 默认分组
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98api.pezayo.comAsk or discussCollected:
Collected this cycle
View 2 plans
coding openai
coding openai group, can call kimi-latest, deepseek-flash models via the openai chat completion format and the openai response format [machine translation]Original: coding openai 分组,能通过 openai chat completion格式和 openai response 格式调用 kimi-latest,deepseek-flash 模型
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98cn.chrouter.comAsk or discussCollected:
Collected this cycle
View 2 plans
gpt
gpt full-series group [machine translation]Original: gpt全系列组
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98codeai.ysaikeji.cnAsk or discussCollected:
Collected this cycle
View 2 plans
default
Default group [machine translation]Original: 默认分组
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98gptapi.asiaAsk or discussCollected:
Collected this cycle
View 2 plans
2 more sites of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

default
Default channel [machine translation]Original: 默认通道
Operator pending verification
212—4.5Median price ÷ this price: 0.6×Full prices and sources
98inferhub.netAsk or discussCollected:
Collected this cycle
View 2 plans
codex5.5
All-round GPT premium pool, fast response, high value for money [machine translation]Original: 全能GPT尊享池相应快,性价比高
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98new.api.yynanshen.topAsk or discussCollected:
Collected this cycle
View 2 plans
GPT Pro stable group [machine translation]Group on site: GPT Pro 稳定分组
GPT Pro stable group [machine translation]Original: GPT Pro 稳定分组
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98nexapi.techAsk or discussCollected:
Collected this cycle
View 3 plans
gpt pro+plus
gpt-pro+plus mixed account pool, stable, high value for money [machine translation]Original: gpt-pro+plus混合号池,稳定高性价比
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98tikbit.aiAsk or discussCollected:
Collected this cycle
View 2 plans
default
Default group, first choice, high value for money, supports Claude, GPT, Gemini, GLM, Kimi, DeepSeek, Grok, MinimaxH3 series and other models. [machine translation]Original: 默认分组,首选使用,性价比高,支持Claude、GPT、Gemini、GLM、Kimi、DeepSeek、Grok、MinimaxH3系列等模型。
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98top.taluna.aiAsk or discussCollected:
Collected this cycle
View 1 plans
codexOperator pending verification2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98unifiedapi.cloudAsk or discussCollected:
Collected this cycle
View 4 plans
acaz
acaz
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98xiaor.xx.kgAsk or discussCollected:
Collected this cycle
View 2 plans
GPT-Pro account pool, split 3 [machine translation]Group on site: GPT-Pro号池 分流3
GPT-Pro account pool, split 3 [machine translation]Original: GPT-Pro号池 分流3
Operator pending verification
2120.24.5Median price ÷ this price: 0.6×Full prices and sources
98api.edu9.usAsk or discussCollected:
Collected this cycle
View 2 plans
GPT Codex pro2 full bundle [machine translation]Group on site: GPT Codex pro2全家桶
OpenAI Codex reverse-engineered, supports Response requests only, supports Lobster (OpenClaw) [machine translation]Original: OpenAI Codex 逆向,仅支持 Response 请求,支持小龙虾
Operator pending verification
2160.25.5Median price ÷ this price: 0.5×Full prices and sources
98cloudreamai.comAsk or discussCollected:
Collected this cycle
View 3 plans
Perk group [machine translation]Group on site: 福利分组
GPT perk channel, ultra-low rate multiplier! The account pool is official Team plans, IQ may occasionally fluctuate [machine translation]Original: GPT福利渠道,超低倍率!号池为官方Team套餐,智商可能偶发波动
Operator pending verification
2160.25.5Median price ÷ this price: 0.5×Full prices and sources
98codexcs.ysaikeji.cnAsk or discussCollected:
Collected this cycle
View 2 plans
codex
codex
Operator pending verification
216—5.5Median price ÷ this price: 0.5×Full prices and sources
98tenzen.aiAsk or discussCollected:
Collected this cycle
View 8 plans
1 more site of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

K3
KIMI-K3
Operator pending verification
2160.25.5Median price ÷ this price: 0.5×Full prices and sources
98www.xiaoyo.cnAsk or discussCollected:
Collected this cycle
View 1 plans
vip
vip group [machine translation]Original: vip分组
Operator pending verification
216—5.5Median price ÷ this price: 0.5×Full prices and sources
121123api.coAsk or discussCollected:
Collected this cycle
View 2 plans
gpt
gpt
Operator pending verification
2.116.8—5.775Median price ÷ this price: 0.5×Full prices and sources
122ai.comfly.orgAsk or discussCollected:
Collected this cycle
View 6 plans
1 more site of the same company

Basis: identical quotes. Counted as one company in the ranking; this is not a legal finding.

default
Default group [machine translation]Original: 默认分组
Operator pending verification
2.5150.255.625Median price ÷ this price: 0.5×Full prices and sources
122aigate8.comAsk or discussCollected:
Collected this cycle
View 1 plans
default
Default group [machine translation]Original: 默认分组
Operator pending verification
2.5150.35.625Median price ÷ this price: 0.5×Full prices and sources
122api.bltcy.aiAsk or discussCollected:
Collected this cycle
View 6 plans
2 more sites of the same company

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
Default group [machine translation]Original: 默认分组
Operator pending verification
2.5150.255.625Median price ÷ this price: 0.5×Full prices and sources
122api.zectai.comAsk or discussCollected:
Collected this cycle
View 1 plans
codex
This group can only use codex series models; rpm is 1000 [machine translation]Original: 此分组只可使用codex系列模型,rpm为1000
Operator pending verification
2.5150.255.625Median price ÷ this price: 0.5×Full prices and sources
Special groups · 14 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: 11 rows
  • unrecognized flag USAGE_IMAGE_ONLY: 2 rows
  • top-up or membership gated: 1 rows
  • ainzy.net · codex-starter · gpt-5.6-terra · Input 0.02 / Output 0.12 USD credits / 1M
  • nty-hk.zhouyang168.top · Codex11 · gpt-5.6-terra · Input 0.02 / Output 0.16 USD credits / 1M
  • yfy.zhouyang168.top · Codex11 · gpt-5.6-terra · Input 0.02 / Output 0.16 USD credits / 1M
  • apiroute.top · gpt-plus · gpt-5.6-terra · Input 0.03375 / Output 0.27 USD credits / 1M
  • ainzy.net · codex-plus · gpt-5.6-terra · Input 0.04 / Output 0.24 USD credits / 1M
  • apiroute.top · gpt-pro · gpt-5.6-terra · Input 0.055 / Output 0.44 USD credits / 1M
  • ainzy.net · codex-pro · gpt-5.6-terra · Input 0.06 / Output 0.36 USD credits / 1M
  • api.pezayo.com · codex · gpt-5.6-terra · Input 0.06 / Output 0.36 USD credits / 1M
  • newtonrouter.com · Gpt Pro 20x · gpt-5.6-terra · Input 0.07 / Output 0.42 USD credits / 1M
  • ainzy.net · codex-ultra · gpt-5.6-terra · Input 0.08 / Output 0.48 USD credits / 1M
View all 14 rows →
Related variants · 3 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

  • gpt-5.6-terra-max (-max · max edition): 3 rows
  • computinger.com · default · gpt-5.6-terra-max · Input 1 / Output 6 USD credits / 1M
  • computinger.com · resale · gpt-5.6-terra-max · Input 1 / Output 6 USD credits / 1M
  • computinger.com · codex · gpt-5.6-terra-max · Input 2 / Output 12 USD credits / 1M
View all 3 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 3593 recorded prices; 705 can be compared directly (683 ranked, 22 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 1853, price not parsed yet 870, display unit not confirmed 64, ratio looks unset 29, billed per request or another unit 26, scope of the official doc price not confirmed 24, new price under review; showing the previous one 1

491 recent · 21 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 OpenAI · gpt-5.6-terra?

ainzy.net, group "codex-enterprise", 0.225 USD credit per million total tokens, observed 2026-10-16. 253 sites have comparable prices.

What is the official price for OpenAI · gpt-5.6-terra?

Input 2, output 12 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 2, output 12 USD per million tokens.

How do I use OpenAI · gpt-5.6-terra in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-5.6-terra API to Claude Code for me". Install Skill →