API PRICES
OpenAI · gpt-4.1
Provider prices, cheapest first
OpenAI · gpt-4.1 official price: not yet recorded. Cheapest inference provider: OpenRouter, input 2, output 8 USD per million tokens. Relays have only older quotes; the lowest is zen-ai.top, group "free" 0.0035 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 105 sites have comparable prices; 179 sites list this model.Relay blended price uses 75% input and 25% output.
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 | 8 | 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.
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 | |||||||
| 18 | api.ai-gaochao.cnAsk or discussCollected: View 20 plans | Evan Evan | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | api.apiyi.comAsk or discussCollected: View 2 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 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | api.bianxie.aiAsk or discussCollected: View 1 plans | default default | 2 | 8 | — | 3.5 | Full prices and sources |
| 18 | api.eido.topAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | api.gravitex.aiAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | api.pezayo.comAsk or discussCollected: View 2 plans | default Default group, use all models via the openai chat completion format [machine translation]Original: 默认分组，通过 openai chat completion 格式使用全部模型 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | api.xhuoai.comAsk or discussCollected: View 2 plans | default 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 | 2 | 8 | — | 3.5 | Full prices and sources |
| 18 | api.xistree.hkAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 2 | 8 | — | 3.5 | Full prices and sources |
| 18 | api.zhiyunai168.comAsk or discussCollected: View 4 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. | Azure Azure gpt series all models, normal concurrency t1key pool, gpt-5.5 not yet supported, gpt-image-2 not yet supported [machine translation]Original: Azure gpt系列全模型，普通并发t1key池，暂不支持gpt-5.5，暂不支持gpt-image-2 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | bita-api-production.up.railway.appAsk or discussCollected: View 1 plans | gpt-origin gpt full suite [machine translation]Original: gpt全家桶 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | codechn.comAsk or discussCollected: View 2 plans | gpt/grok Supported models: gpt, grok [machine translation]Original: 支持模型：gpt、grok | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | happyapi.orgAsk or discussCollected: 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 codex-only group, low-price group can run in bulk [machine translation]Original: codex专用分组，低价分组可批量跑 | 2 | 8 | — | 3.5 | Full prices and sources |
| 18 | llm.azopenai.comAsk or discussCollected: View 1 plans | default default | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | nekoapi.comAsk or discussCollected: View 1 plans 1 more site of the same companyBasis: identical homepage assets, identical quotes. Counted as one company in the ranking; this is not a legal finding. | default Default (Azure + base models) | Azure + Other Base Models [machine translation]Original: 默认（Azure + 基础模型）| Azure + Other Base Models | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | new.yihubang.topAsk or discussCollected: View 3 plans | GPT relay [machine translation]Group on site: GPT 中转 GPT relay [machine translation]Original: GPT 中转 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | newapi.prorisehub.comAsk or discussCollected: View 3 plans | default ⚠️ Default general group: can call every model on the site, don't use it if you don't understand!!! Billing is very expensive!!! [machine translation]Original: ⚠️ 默认通用分组：可调用全站所有模型，不懂别用！！！计费很贵！！！ | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | sg.anyrouter.aiAsk or discussCollected: View 2 plans | default Claude official [machine translation]Original: Claude官 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | tenzen.aiAsk or discussCollected: View 4 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. | gpt-oai | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | yinli.oneAsk or discussCollected: View 8 plans | deepseek Deepseek channel [machine translation]Original: Deepseek渠道 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | yourapi.cnAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 2 | 8 | 0.5 | 3.5 | Full prices and sources |
| 18 | zen-ai.topAsk or discussCollected: View 2 plans | default ✨az official relay + others, 1 yuan per dao (US dollar) [machine translation]Original: ✨az官转+其他模型, 1元一刀 | 2 | 8 | 1 | 3.5 | Full prices and sources |
| 47 | xrok.devAsk or discussCollected: View 2 plans | AZ-GPT AZ GPT supports high concurrency [machine translation]Original: AZ GPT支持高并发 | 2.2 | 8.8 | 0.55 | 3.85 | Full prices and sources |
| 48 | hohoapi.comAsk or discussCollected: View 2 plans | default General channel (most models on the site available) [machine translation]Original: 通用渠道（全站大部分模型可用） | 2.6 | 10.4 | — | 4.55 | Full prices and sources |
| 49 | aws.babyAsk or discussCollected: View 3 plans | Az GPT text [machine translation]Group on site: Az GPT 文本 All models, no image generation [machine translation]Original: 全模型 不带生图 | 2.8 | 11.2 | 0.7 | 4.9 | Full prices and sources |
| 49 | name1.aiAsk or discussCollected: View 1 plans | az gpt special price [machine translation]Group on site: az gpt 特价 | 2.8 | 11.2 | 0.7 | 4.9 | Full prices and sources |
Special groups · 5 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
- internal or channel key: 1 rows
- near-zero-ratio group: 1 rows
- zen-ai.top · free · gpt-4.1 · Input 0.002 / Output 0.008 USD credits / 1M
- new.yihubang.top · Company internal [machine translation]Group on site: 公司内部 · gpt-4.1 · Input 2 / Output 8 USD credits / 1M
- aigcbest.top · Test [machine translation]Group on site: 测试 · gpt-4.1 · Input 7 / Output 28 USD credits / 1M
- api.ifopen.ai · Test [machine translation]Group on site: 测试 · gpt-4.1 · Input 7 / Output 28 USD credits / 1M
- 35.aigcbest.top · Test [machine translation]Group on site: 测试 · gpt-4.1 · Input 16 / Output 64 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 593 recorded prices; 309 can be compared directly (303 ranked, 6 listed separately). Not comparable yet: price not parsed yet 105, new price under review; showing the previous one 87, display unit not confirmed 33, scope of the official doc price not confirmed 29, tiered by rules (see Tiered prices) 25, ratio looks unset 3, billed per request or another unit 2
0 recent · 255 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.