API PRICES

OpenAI · gpt-5.6-sol

Provider prices, cheapest first

Browse all models

OpenAI · gpt-5.6-sol official price: not yet recorded. Cheapest inference provider: OpenRouter, input 4, output 20 USD per million tokens. Relays have only older quotes; the lowest is api.pezayo.com, group "codex anthropic" 0.03375 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 261 sites have comparable prices; 1003 sites list this model.Relay blended price uses 75% input and 25% output.

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 · Aggregator4200.45USD / 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.

sites have comparable prices2611003 sites list this model; approximately 180 operators
Older lowest input price (reference)0.235USD credits / 1M
Median of each provider’s lowest price2.5USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Older price
127xiaocui.eu.orgAsk or discussCollected:
View 2 plans
default
Default group [machine translation]Original: 默认分组
5300.511.25Full prices and sources
127api.foodtomb.eu.orgAsk or discussCollected:
View 2 plans
default
default group [machine translation]Original: default分组
540—13.75Full prices and sources
127api.wlapi.topAsk or discussCollected:
View 2 plans
default
Default group [machine translation]Original: 默认分组
5400.513.75Full prices and sources
127avoapi.comAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
5400.513.75Full prices and sources
127codexcs.ysaikeji.cnAsk or discussCollected:
View 2 plans
codex
codex
540—13.75Full prices and sources
127devinone.comAsk or discussCollected:
View 2 plans
default
Default group [machine translation]Original: 默认分组
5400.513.75Full prices and sources
157hohoapi.comAsk or discussCollected:
View 2 plans
default
General channel (most models on the site available) [machine translation]Original: 通用渠道(全站大部分模型可用)
640.0000000000020.49999999999814.5000000000005Full prices and sources
157brivionix.comAsk or discussCollected:
View 1 plans
default
default - gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.5, gpt-5.6 (codex pro)
6480.64999999999816.5Full prices and sources
159zhongzhuan.usAsk or discussCollected:
View 3 plans
default
Default group [machine translation]Original: 默认分组
6.25500.62517.1875Full prices and sources
160jennyapi.siteAsk or discussCollected:
View 4 plans
GPT-self-built pro account pool [machine translation]Group on site: GPT-自建pro号池
GPT - self-built pro account pool (slightly slower than the enterprise version, intelligence not reduced) [machine translation]Original: GPT-自建pro号池 (速度对比企业版稍慢,不降低智力)
6.652.80.599999999999418.15Full prices and sources
161rivora.ccAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
7.243.20.916.2Full prices and sources
162www.nuwaflux.comAsk or discussCollected:
View 6 plans
gpt- codex
Boutique codex reverse-engineered [machine translation]Original: 精品codex逆向
7.5450.7516.875Full prices and sources
163cloudreamai.comAsk or discussCollected:
View 2 plans
default
Regular user group, GPT series models available [machine translation]Original: 普通用户分组,可用GPT系列模型
9720.924.75Full prices and sources
164aiproxynode.comAsk or discussCollected:
View 2 plans
gptplus
GPT Plus
1060122.5Full prices and sources
164cc.onbb.topAsk or discussCollected:
View 1 plans
oai
openai
1060122.5Full prices and sources
166iai.iisbo.comAsk or discussCollected:
View 5 plans
svipkld
Name on site: [gptpro20x]gpt-5.6-sol
Official relay Claude [machine translation]Original: 官转克劳德
10.833448.75031.0833420.312625Full prices and sources
167128api.cnAsk or discussCollected:
View 2 plans
pro paid all models [machine translation]Group on site: pro付费全模型
Official relay pro models group 1 [machine translation]Original: 官转pro模型1组
11.2156.8—47.6Full prices and sources
168gpt-agent.ccAsk or discussCollected:
View 6 plans
1 more site 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.

codex
codex group [machine translation]Original: codex 分组
12721.227Full prices and sources
168macode.cloudAsk or discussCollected:
View 4 plans
default
Default group [machine translation]Original: 默认分组
1296—33Full prices and sources
170api.getezclaw.comAsk or discussCollected:
View 1 plans
chatgpt
GPT only [machine translation]Original: GPT 專用
12.5751.2528.125Full prices and sources
171api.codex2.ccAsk or discussCollected:
View 2 plans
plus151201.9541.25Full prices and sources
171huskyapi.comAsk or discussCollected:
View 2 plans
codex
Codex group [machine translation]Original: Codex分组
151201.541.25Full prices and sources
173codexcn.topAsk or discussCollected:
View 1 plans
default16128144Full prices and sources
174api.mytokenland.comAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
20160455Full prices and sources
175ai.bytonsec.comAsk or discussCollected:
View 1 plans
KILO
Name on site: openai/gpt-5.6-sol
24120—48Full prices and sources
Special groups · 23 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.

  • test or debug group: 11 rows
  • near-zero-ratio group: 10 rows
  • marked display-only or do-not-select: 8 rows
  • internal or channel key: 1 rows
  • top-up or membership gated: 1 rows
  • api.pezayo.com · codex anthropic · gpt-5.6-sol · Input 0.015 / Output 0.09 USD credits / 1M
  • nty-hk.zhouyang168.top · Codex11 · gpt-5.6-sol · Input 0.04 / Output 0.32 USD credits / 1M
  • yfy.zhouyang168.top · Codex11 · gpt-5.6-sol · Input 0.04 / Output 0.32 USD credits / 1M
  • apiroute.top · gpt-plus · gpt-5.6-sol · Input 0.0675 / Output 0.54 USD credits / 1M
  • apiroute.top · gpt-pro · gpt-5.6-sol · Input 0.11 / Output 0.88 USD credits / 1M
  • ainzy.net · codex-plus · gpt-5.6-sol · Input 0.12 / Output 0.6 USD credits / 1M
  • bmodels.top · default · gpt-5.6-sol · Input 0.128 / Output 0.8 USD credits / 1M
  • api.pezayo.com · codex · gpt-5.6-sol · Input 0.15 / Output 0.9 USD credits / 1M
  • newtonrouter.com · Gpt Pro 20x · gpt-5.6-sol · Input 0.175 / Output 1.05 USD credits / 1M
  • ai.sggai.site · test · gpt-5.6-sol · Input 1 / Output 6 USD credits / 1M
View all 23 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-sol-max (-max · max edition): 3 rows
  • computinger.com · resale · gpt-5.6-sol-max · Input 5 / Output 30 USD credits / 1M
  • computinger.com · default · gpt-5.6-sol-max · Input 5 / Output 30 USD credits / 1M
  • computinger.com · codex · gpt-5.6-sol-max · Input 10 / Output 60 USD credits / 1M
View all 3 rows →
How this ranking works

All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.

This model has 4004 recorded prices; 718 can be compared directly (687 ranked, 31 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 2191, price not parsed yet 655, new price under review; showing the previous one 259, display unit not confirmed 91, billed per request or another unit 34, ratio looks unset 30, scope of the official doc price not confirmed 26

0 recent · 540 stale (older than 7 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 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 →

Switch model