API PRICES
OpenAI · gpt-5.6-sol
Provider prices, cheapest first
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
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | 4 | 20 | 0.4 | 5 | USD / 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 providersRelays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Older price | |||||||
| 156 | mochiapi.comAsk or discussCollected: View 1 plans | vip2_pro |c:indigo||s:5| Codex (external use allowed, Pro account pool, tenfold compensation if fake) [machine translation]Original: |c:indigo||s:5| Codex (可外接 Pro号池 假一赔十) | 1.5 | 12 | 0.15 | 4.125 | Full prices and sources |
| 156 | synai996.spaceAsk or discussCollected: View 3 plans | Codex_GPT_BPS [not dumbed down] [machine translation]Group on site: Codex_GPT_BPS[不降智] Not dumbed down group, trial of Excel channel requests, slightly smaller context [machine translation]Original: 不降智分组,试用 Excel 渠道请求 上下文略小 | 1.5 | 12 | 0.15 | 4.125 | Full prices and sources |
| 156 | synai996.spaceAsk or discussCollected: View 3 plans | Codex_GPT_PRO [No jailbreak] PRO account pool channel - for full-strength Codex models only, supports cache/1M [machine translation]Original: [禁止破限]PRO号池渠道—满血Codex模型专用、支持缓存/1M | 1.5 | 12 | 0.15 | 4.125 | Full prices and sources |
| 179 | torchai.aiAsk or discussCollected: View 3 plans | codex-pro (backup) [machine translation]Group on site: codex-pro(备用) | 1.65 | 9.9 | 0.165 | 3.7125 | Full prices and sources |
| 180 | ai.luminai.ccAsk or discussCollected: View 4 plans 2 more sites of the same companyBasis: 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. | B-Codex-B [Codex] Fairly fast; you can run the pelican test before use; listed as an extension channel [machine translation]Original: 【Codex】速度较快 用前可测鹈鹕 作为拓展渠道上架 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | api.aipaibox.comAsk or discussCollected: View 3 plans | gpt pro group [machine translation]Group on site: gpt pro分组 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | api.seanzan.comAsk or discussCollected: View 2 plans | gpt-pro | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | deepkey.topAsk or discussCollected: View 14 plans | gpt-openai4 gpt-openai-official KEY-codex only-has cache creation-perk [machine translation]Original: gpt-openai-官KEY-codex专用-有创建缓存-福利 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | ggniao.comAsk or discussCollected: View 5 plans | OpenAI channel 3 [machine translation]Group on site: OpenAI 渠道3 Enterprise-grade stable channel, pro account pool [machine translation]Original: 企业级稳定通道,pro号池 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | mzlone.topAsk or discussCollected: View 6 plans | codex codex: official Codex channel, gpt-5.x, gpt-5.x-codex, xhigh etc. all supported, Pro+Plus [machine translation]Original: codex:官方 Codex 渠道,gpt-5.x,gpt-5.x-codex,xhigh等全部支持 Pro+Plus | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | sxcode.onlineAsk or discussCollected: View 3 plans | codex-grok-to-codex grok models mapped to gpt models, usable directly in codex [machine translation]Original: grok模型映射成gpt模型,可在codex中直接使用 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | windapi.ccAsk or discussCollected: View 2 plans | GPT stable group [machine translation]Group on site: GPT稳定分组 100% pure PRO account pool, stability guaranteed. [machine translation]Original: 百分百纯PRO号池,保证稳定。 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | api.luminai.ccAsk or discussCollected: View 4 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. | B-Codex-B [Codex] Fairly fast; you can run the pelican test before use; listed as an extension channel [machine translation]Original: 【Codex】速度较快 用前可测鹈鹕 作为拓展渠道上架 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 180 | vip.luminai.ccAsk or discussCollected: View 4 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. | B-Codex-B [Codex] Fairly fast; you can run the pelican test before use; listed as an extension channel [machine translation]Original: 【Codex】速度较快 用前可测鹈鹕 作为拓展渠道上架 | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 190 | llm.kagu.oneAsk or discussCollected: View 3 plans | Hodgepodge [machine translation]Group on site: 大杂烩 Name on site: openai/gpt-5.6-sol | 1.875 | 11.25 | 0.1875 | 4.21875 | Full prices and sources |
| 190 | llm.kagu.oneAsk or discussCollected: View 3 plans | Hodgepodge [machine translation]Group on site: 大杂烩 | 1.875 | 15 | 0.1875 | 5.15625 | Full prices and sources |
| 192 | vbcode.ioAsk or discussCollected: View 4 plans | codex [pro account pool] Pure PRO account pool. Very high cache hit rate (used in codex). Choose this group for codex/gpt; can connect third-party apps, e.g. Lobster (OpenClaw)/cherry studio/chatbox; see docs for configuration [machine translation]Original: [pro账户号池] 纯PRO账户号池。缓存命中极高(codex中使用). codex/gpt选择这个分组, 可外接第三方应用, 例如龙虾/cherry studio/chatbox, 详见文档配置 | 2 | 10 | 0.2 | 4 | Full prices and sources |
| 192 | xiaoma.bestAsk or discussCollected: View 2 plans | gpt GPT full series (0.5x the default channel's price) - gpt full-series models (no image generation), no claude or gemini [machine translation]Original: GPT 全系列(默认渠道的0.5倍价格) - gpt全系列模型(没有生图),没有claude和gemini | 2 | 10 | 0.2 | 4 | Full prices and sources |
| 192 | xiaoma.bestAsk or discussCollected: View 2 plans | gpt Name on site: gpt-5.6-sol-xhigh GPT full series (0.5x the default channel's price) - gpt full-series models (no image generation), no claude or gemini [machine translation]Original: GPT 全系列(默认渠道的0.5倍价格) - gpt全系列模型(没有生图),没有claude和gemini | 2 | 10 | 0.2 | 4 | Full prices and sources |
| 192 | ai.luminai.ccAsk or discussCollected: View 4 plans 2 more sites of the same companyBasis: 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. | B-Codex-Plus [Codex] Plus account pool + Pro!! Highly stable for long-term use, high cache, top choice for enterprises and individuals, OpenClew, Hermes [machine translation]Original: 【Codex】Plus号池+Pro!!稳定高长期使用,高缓存,企业个人首选 OpenClew、Hermes | 2 | 12 | 0.2 | 4.5 | Full prices and sources |
| 192 | api.onefaka.comAsk or discussCollected: View 6 plans | codex codex ultra-stable [machine translation]Original: codex超稳 | 2 | 12 | 0.2 | 4.5 | Full prices and sources |
| 192 | ycyapi.cnAsk or discussCollected: View 6 plans | 11-GPT official relay KEY [machine translation]Group on site: 11-GPT 官转KEY Official relay - not dumbed down [machine translation]Original: 官转-不降智 | 2 | 12 | 0.22 | 4.5 | Full prices and sources |
| 192 | api.luminai.ccAsk or discussCollected: View 4 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. | B-Codex-Plus [Codex] Plus account pool + Pro!! Highly stable for long-term use, high cache, top choice for enterprises and individuals, OpenClew, Hermes [machine translation]Original: 【Codex】Plus号池+Pro!!稳定高长期使用,高缓存,企业个人首选 OpenClew、Hermes | 2 | 12 | 0.2 | 4.5 | Full prices and sources |
| 192 | vip.luminai.ccAsk or discussCollected: View 4 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. | B-Codex-Plus [Codex] Plus account pool + Pro!! Highly stable for long-term use, high cache, top choice for enterprises and individuals, OpenClew, Hermes [machine translation]Original: 【Codex】Plus号池+Pro!!稳定高长期使用,高缓存,企业个人首选 OpenClew、Hermes | 2 | 12 | 0.2 | 4.5 | Full prices and sources |
| 192 | ai.augmen.netAsk or discussCollected: View 3 plans | codex pro codex pro | 2 | 16 | 0.24 | 5.5 | Full 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
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
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.