API PRICES
OpenAI · gpt-3.5-turbo
Tiered prices, cheapest first
Price ranges per million tokens
Official cash prices · Lowest 0.75 · median 0.75 · highest 0.75 · 1 quotes USD / per million tokens
Inference provider cash prices · Lowest 0.75 · median 0.75 · highest 0.75 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 0.21875 · median 0.75 · highest 3.75 · 38 quotes USD / per million tokens, site credit
Relay CNY credit prices · Lowest 0.25 · median 1.4614 · highest 8.4231 · 13 quotes CNY / per million tokens, site credit
Uses the standard tier (shortest context, base price). Full rules are in Details.
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | wolfai.topAsk or discussCollected: Collected this cycle View 2 plans | Azure Standard tier · standard Claude+OpenAI | Microsoft Azure pure-blood (all official) official relay channel [machine translation]Original: Claude+OpenAI｜微软 Azure 纯血官转渠道 Operator pending verification | 0.375 | 1.125 | 0 | 0.5625 | Full prices and sources |
| 02 | home.moleapi.comAsk or discussCollected: Collected this cycle View 2 plans | discount Standard tier · base Special price [machine translation]Original: 特价 Operator pending verification | 0.4 | 1.2 | — | 0.6 | Full prices and sources |
| 03 | witflow.aiAsk or discussCollected: Collected this cycle View 3 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. | CodeX Slb exclusive [machine translation]Group on site: CodeX Slb专属 Standard tier · standard For Codex CLI only, not for general chat. When using Codex CLI be sure to select the "Codex exclusive" group, otherwise original price applies (×1 rate multiplier) [machine translation]Original: 仅用于 Codex CLI，不可用于通用对话。用 Codex CLI一定选「Codex专属」分组，否则走原价(×1倍率) Operator pending verification | 0.5 | 1.5 | 0 | 0.75 | Full prices and sources |
| 04 | ai.bytonsec.comAsk or discussCollected: Collected this cycle View 1 plans | VERCEL Standard tier · standard Operator pending verification | 3 | 9 | — | 4.5 | Full prices and sources |
| Older price | |||||||
| 01 | api.101aix.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 1 plans | OpenAI Standard tier · standard OpenAI|pure OpenAI official native KEY [machine translation]Original: OpenAI|纯OpenAI官方原生KEY Operator pending verification | 0.5 | 1.5 | — | 0.75 | Full prices and sources |
How this ranking works
All tiered prices: 32,301 prices from 636 sites (about 556 companies). 30,366 are ranked, from 631 sites (about 551 companies); 1,935 more are listed separately and not ranked. Prices collected up to 2026-10-24.
This model has 12 tiered prices; 12 can be compared directly.
11 recent · 1 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.
For tiered models (e.g. longer context costs more) we use the standard tier: shortest context, normal service tier, base price without promotions. Prices that change with time of day or request options are listed separately with the reason. See “Details” for the full rules.
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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for OpenAI · gpt-3.5-turbo?
cdn.yorhamc.com, group "default", 0.21875 USD credit per million total tokens, observed 2026-10-23. 80 sites have comparable prices.
What is the official price for OpenAI · gpt-3.5-turbo?
Input 0.5, output 1.5 USD per million tokens, checked 2026-10-24. Lowest inference provider: OpenRouter, input 0.5, output 1.5 USD per million tokens.
How do I use OpenAI · gpt-3.5-turbo in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-3.5-turbo API to Claude Code for me". Install Skill →