API PRICES
OpenAI · gpt-5.3-codex
Provider prices, cheapest first
OpenAI · gpt-5.3-codex official price: input 1.75, output 14.00 USD per million tokens (OpenAI, observed 2026-10-16). Cheapest inference provider: OpenRouter, input 1.75, output 14 USD per million tokens. Relays have only older quotes; the lowest is api.pezayo.com, group "codex" 0.144375 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 134 sites have comparable prices; 233 sites list this model.Relay blended price uses 75% input and 25% output.
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| OpenAI | 1.75 | 14.00 | 0.175 | — | USD / 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
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | 1.75 | 14 | 0.175 | — | USD / 1M tokens | Official source | Input 0% · Output 0% |
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 | |||||||
| 26 | api.edu9.usAsk or discussCollected: 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 | 1.2 | 9.6 | 0.0800000000004 | 3.3 | Full prices and sources |
| 27 | api.deepai.wangAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.25 | 7.5 | — | 2.8125 | Full prices and sources |
| 27 | aiincs.netAsk or discussCollected: View 1 plans 1 more site 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. | default Default group [machine translation]Original: 默认分组 | 1.25 | 10 | 0.125 | 3.4375 | Full prices and sources |
| 29 | api.hopeai.ccAsk or discussCollected: View 1 plans | codex stable group [machine translation]Group on site: codex稳定组 | 1.4 | 11.2 | 0.1225 | 3.85 | Full prices and sources |
| 30 | gptapi.asiaAsk or discussCollected: View 2 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. | default Default channel [machine translation]Original: 默认通道 | 1.408 | 11.264 | — | 3.872 | Full prices and sources |
| 31 | cnapi.kksj.orgAsk or discussCollected: View 4 plans | default Default group, AZ channel plus official reverse-engineered channel for some models, AZ first, reverse-engineered as fallback, auto-tuning (default) [machine translation]Original: 默认分组,AZ渠道加部分模型官方逆向渠道,优先AZ,保底逆向,自动调优(default) | 1.575 | 12.6 | 0.1575 | 4.33125 | Full prices and sources |
| 31 | www.cybersol.netAsk or discussCollected: View 3 plans | Azure Based on Azure Openai's, low-rate version. If an image model returns a sexual error, it is disabled for 24 hours. [machine translation]Original: 基于Azure Openai's，低速率版。生图模型如果出现sexual报错，会被禁用24小时。 | 1.575 | 12.6 | 0.207000000000675 | 4.33125 | Full prices and sources |
| 33 | aiapi.worldAsk or discussCollected: View 1 plans | default default | 1.74267 | 13.94136 | — | 4.7923425 | Full prices and sources |
| 34 | aiproxynode.comAsk or discussCollected: View 2 plans | gptplus GPT Plus | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 34 | api.aabao.topAsk or discussCollected: View 8 plans 1 more site of the same companyBasis: 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 (1.0x rate multiplier) [machine translation]Original: 默认分组（1.0倍率） | 1.75 | 10.5 | 0.175 | 3.9375 | Full prices and sources |
| 34 | 123api.coAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.75 | 14 | — | 4.8125 | Full prices and sources |
| 34 | 35.aigcbest.topAsk or discussCollected: View 2 plans | default ⭐ Recommended | all-model automatic load optimization, highest availability [machine translation]Original: ⭐ 推荐 | 全模型自动负载优化最高可用性 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | ai.comfly.orgAsk or discussCollected: View 24 plans 1 more site of the same companyBasis: identical quotes. Counted as one company in the ranking; this is not a legal finding. | default Name on site: gpt-5.3-codex-medium Default group [machine translation]Original: 默认分组 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | aigcbest.topAsk or discussCollected: View 2 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | default ⭐ Recommended | all-model automatic load optimization [machine translation]Original: ⭐ 推荐 | 全模型自动负载优化 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | airouter.cloudAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.2slk.comAsk or discussCollected: View 1 plans | Official relay [machine translation]Group on site: 官转 Official API forwarding [machine translation]Original: 官方API转发 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.bianxie.aiAsk or discussCollected: View 1 plans | default default | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.eido.topAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.75 | 14 | 0.28 | 4.8125 | Full prices and sources |
| 34 | api.foodtomb.eu.orgAsk or discussCollected: View 4 plans | default default group [machine translation]Original: default分组 | 1.75 | 14 | — | 4.8125 | Full prices and sources |
| 34 | api.gravitex.aiAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.guaiyun.ccAsk or discussCollected: View 2 plans | default Currently supports gemini-3.1-flash-image-preview, gpt-image-2. [machine translation]Original: 目前支持gemini-3.1-flash-image-preview、gpt-image-2。 | 1.75 | 14 | 0.17999975 | 4.8125 | Full prices and sources |
| 34 | api.mixrai.comAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.onefaka.comAsk or discussCollected: View 5 plans | c15 Claude Channel 15 Only | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.pezayo.comAsk or discussCollected: View 3 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 | 1.75 | 14 | 0.175 | 4.8125 | Full prices and sources |
| 34 | api.xhuoai.comAsk or discussCollected: View 10 plans | default Name on site: gpt-5.3-codex-high Default group, supports all common models, OpenAI special-price channel (AZ Microsoft channel) Claude Code, Gemini stable channel (GCP/Velax), top value-for-money choice, 20% of list price, rate multiplier 1.0 [machine translation]Original: 默认分组，支持所有常用模型,OpenAI特价渠道（AZ微软渠道）Claude Code,Gemini稳定渠道（GCP/Velax），性价比首选，2折，倍率1.0 | 1.75 | 14 | — | 4.8125 | Full prices and sources |
Special groups · 7 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: 3 rows
- near-zero-ratio group: 2 rows
- internal or channel key: 1 rows
- top-up or membership gated: 1 rows
- api.pezayo.com · codex · gpt-5.3-codex · Input 0.0525 / Output 0.42 USD credits / 1M
- buliangrenai.com · gpt-0.036 · gpt-5.3-codex · Input 0.063 / Output 0.504 USD credits / 1M
- new.yihubang.top · Company internal [machine translation]Group on site: 公司内部 · gpt-5.3-codex · Input 1.75 / Output 14 USD credits / 1M
- api.edu9.us · shareVIP-only codex [machine translation]Group on site: shareVIP专用codex · gpt-5.3-codex · Input 3 / Output 24 USD credits / 1M
- aigcbest.top · Test [machine translation]Group on site: 测试 · gpt-5.3-codex · Input 6.125 / Output 49 USD credits / 1M
- api.ifopen.ai · Test [machine translation]Group on site: 测试 · gpt-5.3-codex · Input 6.125 / Output 49 USD credits / 1M
- 35.aigcbest.top · Test [machine translation]Group on site: 测试 · gpt-5.3-codex · Input 14 / Output 112 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 1039 recorded prices; 528 can be compared directly (521 ranked, 7 listed separately). Not comparable yet: new price under review; showing the previous one 172, price not parsed yet 134, scope of the official doc price not confirmed 99, display unit not confirmed 47, tiered by rules (see Tiered prices) 39, ratio looks unset 16, billed per request or another unit 4
0 recent · 477 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.