API PRICES
OpenAI · gpt-5.5
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 5 / output 30 USD/million tokensOpenAI ·
- Lowest inference provider (cash)
- Input 5 / output 30 USD/million tokensOpenRouter · Aggregator ·
- Lowest relay (credit)
- 1.6875 USD credit/million total tokensapi.starchenapi.xyz "gptplus" ·
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-5.5 official price: input 5, output 30 USD per million tokens (OpenAI, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 5, output 30 USD per million tokens. Cheapest relay: api.starchenapi.xyz, group "gptplus" 1.6875 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 364 sites have comparable prices; 814 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 11.25 · median 15 · highest 18.75 · 2 quotes USD / per million tokens
Inference provider cash prices · Lowest 11.25 · median 11.25 · highest 11.25 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 1.6875 · median 3.375 · highest 33.75 · 5 quotes USD / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| OpenAI | 5 | 30 | 0.5 | — | USD / 1M tokens | Official source | |
| OpenAI | 10 | 45 | 1 | — | 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 | 5 | 30 | 0.5 | — | 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.
Price range: lowest 1.6875 · median 3.375 · highest 33.75 (5 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 |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | api.starchenapi.xyzAsk or discussCollected: Collected this cycle View 5 plans | gptplus Full-strength gpt5.5 5.6 [machine translation]Original: 满血gpt5.5 5.6 Operator pending verification | 0.75 | 4.5 | 0.075 | 1.6875Median price ÷ this price: 2× | Full prices and sources |
| 02 | api.starchenapi.xyzAsk or discussCollected: Collected this cycle View 5 plans | gptpro perk group [machine translation]Group on site: gptpro福利组 Pure pro pool, ultra-fast and reliable, special price; switch to pro yourself when unstable [machine translation]Original: 纯pro池，极速可靠，特价，不稳定时请自己切换到pro Operator pending verification | 1.2 | 7.2 | 0.12 | 2.7Median price ÷ this price: 1.3× | Full prices and sources |
| 03 | api.starchenapi.xyzAsk or discussCollected: Collected this cycle View 5 plans | gpt-pro group [machine translation]Group on site: gpt-pro分组 GPT PRO 20 enterprise exclusive, stable, not dumbed down, supports 5.6 codex spark [machine translation]Original: GPT PRO 20企业专享，稳定，不降智，支持5.6 codex spark Operator pending verification | 1.5 | 9 | 0.15 | 3.375Median price ÷ this price: 1× | Full prices and sources |
| 03 | api.starchenapi.xyzAsk or discussCollected: Collected this cycle View 5 plans | image-2 gpt-image2 image generation supports 1k, 2k, 4k [machine translation]Original: gpt-image2生图支持1k，2k，4k Operator pending verification | 1.5 | 9 | 0.15 | 3.375Median price ÷ this price: 1× | Full prices and sources |
| 05 | api.starchenapi.xyzAsk or discussCollected: Collected this cycle View 5 plans | az gpt az gpt for enterprise use, absolutely stable [machine translation]Original: 企业用az gpt绝对稳定 Operator pending verification | 15 | 90 | 1.5 | 33.75Median price ÷ this price: 0.1× | Full prices and sources |
Special groups · 13 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: 6 rows
- unrecognized flag USAGE_IMAGE_ONLY: 3 rows
- test or debug group: 2 rows
- Free declaration, listed separately: 1 rows
- top-up or membership gated: 1 rows
- zero-ratio group: 1 rows
- api.nexl.cn · vip · gpt-5.5 · Input 0 / Output 0 USD credits / 1M
- api.pezayo.com · codex anthropic · gpt-5.5 · Input 0.015 / Output 0.09 USD credits / 1M
- apiroute.top · gpt-plus · gpt-5.5 · Input 0.0675 / Output 0.405 USD credits / 1M
- apiroute.top · gpt-pro · gpt-5.5 · Input 0.11 / Output 0.66 USD credits / 1M
- bmodels.top · default · gpt-5.5 · Input 0.128 / Output 0.8 USD credits / 1M
- api.pezayo.com · codex · gpt-5.5 · Input 0.15 / Output 0.9 USD credits / 1M
- newtonrouter.com · Gpt Pro 20x · gpt-5.5 · Input 0.175 / Output 1.05 USD credits / 1M
- bikip.pro · ductest · gpt-5.5-xhigh · Input 1.5 / Output 9 USD credits / 1M
- bikip.pro · ductest · gpt-5.5 · Input 1.5 / Output 9 USD credits / 1M
- apiapi.gptshare666.pro · Image-generation-only API [machine translation]Group on site: 画图专用API · gpt-5.5 · Input 2.5 / Output 15 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 2875 recorded prices; 1026 can be compared directly (1008 ranked, 18 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 1034, price not parsed yet 569, ratio looks unset 74, display unit not confirmed 67, billed per request or another unit 41, scope of the official doc price not confirmed 26, new price under review; showing the previous one 2
5 recent · 0 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-5.5?
api.starchenapi.xyz, group "gptplus", 1.6875 USD credit per million total tokens, observed 2026-10-16. 364 sites have comparable prices.
What is the official price for OpenAI · gpt-5.5?
Input 5, output 30 USD per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 5, output 30 USD per million tokens.
How do I use OpenAI · gpt-5.5 in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-5.5 API to Claude Code for me". Install Skill →