API PRICES
OpenAI · gpt-4o
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 2.5 / output 10 USD/million tokensOpenAI ·
- Lowest inference provider (cash)
- Input 2.5 / output 10 USD/million tokensOpenRouter · Aggregator · same as official ·
- Lowest relay (credit)
- Older reference: 3.5 USD credit/million total tokenskg-api.cloud "vip" ·
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-4o official price: input 2.5, output 10 USD per million tokens (OpenAI, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 2.5, output 10 USD per million tokens. Relays have only older quotes; the lowest is kg-api.cloud, group "vip" 3.5 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 113 sites have comparable prices; 198 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 4.375 · median 4.375 · highest 4.375 · 1 quotes USD / per million tokens
Inference provider cash prices · Lowest 4.375 · median 4.375 · highest 4.375 · 1 quotes USD / per million tokens
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| OpenAI | 2.5 | 10 | 1.25 | — | 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 | 2.5 | 10 | 1.25 | — | 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.
Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)
Relays
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 | |||||||
| 01 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | vip Reverse-engineered, usage-based (vip) [machine translation]Original: 逆向按量(vip) Operator pending verification | 2 | 8 | 1 | 3.5 | Full prices and sources |
| 02 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | default Default group [machine translation]Original: 默认分组 Operator pending verification | 2.5 | 10 | 1.25 | 4.375 | Full prices and sources |
| 02 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | svip Pure Azure [machine translation]Original: 纯Azure Operator pending verification | 2.5 | 10 | 1.25 | 4.375 | Full prices and sources |
| 02 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | vvip Reverse-engineered, per-request (vvip) [machine translation]Original: 逆向按次(vvip) Operator pending verification | 2.5 | 10 | 1.25 | 4.375 | Full prices and sources |
| 05 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | AZ-premium quality [machine translation]Group on site: AZ-优质 Pure Azure-premium quality, supports o1, o3 [machine translation]Original: 纯Azure-优质，支持o1、o3 Operator pending verification | 3.75 | 15 | 1.875 | 6.5625 | Full prices and sources |
| 06 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | ssvip Pure OpenAI, special-price group [machine translation]Original: 纯OpenAI，特价分组 Operator pending verification | 7.5 | 30 | 3.75 | 13.125 | Full prices and sources |
| 07 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | openai official-premium quality [machine translation]Group on site: openai官-优质 Pure OpenAI, special-price premium-quality group [machine translation]Original: 纯OpenAI，特价优质分组 Operator pending verification | 10 | 40 | 5 | 17.5 | Full prices and sources |
| 08 | kg-api.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 8 plans | origin Enterprise group (origin)-OpenAI&Claude official price [machine translation]Original: 企业分组(origin)-OpenAI&Claude官方原价 Operator pending verification | 18.25 | 73 | 9.125 | 31.938 | Full prices and sources |
Special groups · 2 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: 1 rows
- test or debug group: 1 rows
- zen-ai.top · free · gpt-4o · Input 0.0025 / Output 0.01 USD credits / 1M
- test-api.apiqik.online · openai · gpt-4o · Input 0.75 / Output 3 USD credits / 1M
Related variants · 9 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-4o-search (-search · search or tool): 9 rows
- 35.aigcbest.top · default · gpt-4o-search · Input 5 / Output 15 USD credits / 1M
- aigcbest.top · default · gpt-4o-search · Input 5 / Output 15 USD credits / 1M
- api.ifopen.ai · default · gpt-4o-search · Input 5 / Output 15 USD credits / 1M
- api2.aigcbest.top · default · gpt-4o-search · Input 5 / Output 15 USD credits / 1M
- api.hopeai.cc · default · gpt-4o-search · Input 5 / Output 20 USD credits / 1M
- aigcbest.top · All-model dedicated line channel [machine translation]Group on site: 全模型专线渠道 · gpt-4o-search · Input 13 / Output 39 USD credits / 1M
- api.ifopen.ai · All-model dedicated line channel [machine translation]Group on site: 全模型专线渠道 · gpt-4o-search · Input 13 / Output 39 USD credits / 1M
- api2.aigcbest.top · All-model dedicated line channel [machine translation]Group on site: 全模型专线渠道 · gpt-4o-search · Input 13 / Output 39 USD credits / 1M
- 35.aigcbest.top · Top-speed channel [machine translation]Group on site: 极速通道 · gpt-4o-search · Input 40 / Output 120 USD credits / 1M
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 649 recorded prices; 327 can be compared directly (314 ranked, 13 listed separately). Not comparable yet: price not parsed yet 202, scope of the official doc price not confirmed 33, tiered by rules (see Tiered prices) 24, billed per request or another unit 22, display unit not confirmed 20, ratio looks unset 12
0 recent · 8 stale (older than 10 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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for OpenAI · gpt-4o?
No valid quotes within 10 days. Older quotes are listed as reference prices.
What is the official price for OpenAI · gpt-4o?
Input 2.5, output 10 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 2.5, output 10 USD per million tokens. Input 0% higher than official.
How do I use OpenAI · gpt-4o in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-4o API to Claude Code for me". Install Skill →