API PRICES
OpenAI · gpt-5.4-mini
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 0.75 / output 4.5 USD/million tokensOpenAI ·
- Lowest inference provider (cash)
- Input 0.75 / output 4.5 USD/million tokensOpenRouter · Aggregator · same as official ·
- Lowest relay (credit)
- 0.084375 USD credit/million total tokensbuliangrenai.com "gpt-0.05" ·
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-5.4-mini official price: input 0.75, output 4.5 USD per million tokens (OpenAI, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 0.75, output 4.5 USD per million tokens. Cheapest relay: buliangrenai.com, group "gpt-0.05" 0.084375 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 260 sites have comparable prices; 416 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 1.6875 · median 1.6875 · highest 1.6875 · 1 quotes USD / per million tokens
Inference provider cash prices · Lowest 1.6875 · median 1.6875 · highest 1.6875 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 0.084375 · median 1.35 · highest 27 · 143 quotes USD / per million tokens, site credit
Relay CNY credit prices · Lowest 0.10226 · median 1.1363 · highest 18.952 · 44 quotes CNY / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| OpenAI | 0.75 | 4.5 | 0.075 | — | 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 | 0.75 | 4.5 | 0.075 | — | 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 0.084375 · median 1.35 · highest 27 (143 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 |
|---|---|---|---|---|---|---|---|
| Flagged · not ranked · Recent price | |||||||
| — | officesai.topAsk or discussCollected: Collected this cycle View 3 plans | Codex GPT Pro All full-price Pro account pool, high stability | full-strength, full cache | GPT-5 core architecture, fully autonomous task agent, extreme Token compression ratio [machine translation]Original: 全正价Pro号池 高稳定 | 满血满缓存 | GPT-5 核心架构、全自主任务代理、极致 Token 压缩率 Note: number precision issue. This price is not ranked or counted. Operator pending verification | 2.075 | 12.5 | 0.2075 | 4.6812Median price ÷ this price: 0.3× | Full prices and sources |
| — | 1xm.aiAsk or discussCollected: Collected this cycle View 2 plans | az-gpt gpt via Azure cloud direct connection, high stability, high cache; for emergencies when account pools are unstable [machine translation]Original: Azure云直联的 gpt，稳定性高，缓存高，号池不稳定时应急用 Note: number precision issue. This price is not ranked or counted. Operator pending verification | 2.1 | 12.6 | 0.21 | 4.725Median price ÷ this price: 0.3× | Full prices and sources |
| — | kaiycb.comAsk or discussCollected: Collected this cycle View 4 plans | gpt imga2 image generation [machine translation]Group on site: gpt imga2生图 Note: number precision issue. This price is not ranked or counted. Operator pending verification | 7.5 | 45 | 0.75 | 16.875Median price ÷ this price: 0.1× | Full prices and sources |
| Flagged · not ranked · Older price | |||||||
| — | kktyh.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 2 plans | GPT3 mixed pool [machine translation]Group on site: GPT3-混合池 Includes Team, K12, Plus; this is a mixed pool. [machine translation]Original: 包含Team、K12、Plus，这是一个混合的池子。 Note: number precision issue. This price is not ranked or counted. Operator pending verification | 0.105 | 0.63 | 0.0105 | 0.23625Median price ÷ this price: 5.7× | Full prices and sources |
| — | kktyh.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 2 plans | GPT1-Pro Includes Pro; this is a pure Pro pool. [machine translation]Original: 包含Pro，这是一个纯Pro的池子。 Note: number precision issue. This price is not ranked or counted. Operator pending verification | 0.165 | 0.99 | 0.0165 | 0.37125Median price ÷ this price: 3.6× | Full prices and sources |
| — | relay.nccnxta.cnAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 1 plans | Test group [machine translation]Group on site: 测试分组 For testing, do not select, do not select!!! [machine translation]Original: 测试用的 不要选 不要选!!! Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 7,500 | 45,000 | 750 | 16,875Median price ÷ this price: 0× | Full prices and sources |
Special groups · 9 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: 4 rows
- unrecognized flag USAGE_IMAGE_ONLY: 2 rows
- Free declaration, listed separately: 1 rows
- ratio looks like a placeholder: 1 rows
- top-up or membership gated: 1 rows
- zero-ratio group: 1 rows
- api.nexl.cn · vip · gpt-5.4-mini · Input 0 / Output 0 USD credits / 1M
- api.pezayo.com · codex anthropic · gpt-5.4-mini · Input 0.00225 / Output 0.0135 USD credits / 1M
- apiroute.top · gpt-plus · gpt-5.4-mini · Input 0.010125 / Output 0.06075 USD credits / 1M
- apiroute.top · gpt-pro · gpt-5.4-mini · Input 0.0165 / Output 0.099 USD credits / 1M
- api.pezayo.com · codex · gpt-5.4-mini · Input 0.0225 / Output 0.135 USD credits / 1M
- newapi.13791888.xyz · Image generation only group [machine translation]Group on site: 生图专用分组 · gpt-5.4-mini · Input 0.75 / Output 4.5 USD credits / 1M
- api.edu9.us · shareVIP-only codex [machine translation]Group on site: shareVIP专用codex · gpt-5.4-mini · Input 1.5 / Output 9 USD credits / 1M
- newapi.13791888.xyz · 4k image generation group [machine translation]Group on site: 4k生图分组 · gpt-5.4-mini · Input 1.8 / Output 10.8 USD credits / 1M
- api.manai8.xyz · Exclusive to teacher Daxia [machine translation]Group on site: 大虾老师专属 · gpt-5.4-mini · Input 75 / Output 450 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 1117 recorded prices; 613 can be compared directly (602 ranked, 11 listed separately). Not comparable yet: price not parsed yet 271, tiered by rules (see Tiered prices) 110, ratio looks unset 40, display unit not confirmed 32, scope of the official doc price not confirmed 25, billed per request or another unit 5, new price under review; showing the previous one 1
443 recent · 25 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-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-5.4-mini?
buliangrenai.com, group "gpt-0.05", 0.084375 USD credit per million total tokens, observed 2026-10-16. 260 sites have comparable prices.
What is the official price for OpenAI · gpt-5.4-mini?
Input 0.75, output 4.5 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 0.75, output 4.5 USD per million tokens. Input 0% higher than official.
How do I use OpenAI · gpt-5.4-mini in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-5.4-mini API to Claude Code for me". Install Skill →