API PRICES
OpenAI · gpt-4.1-mini
Provider prices, cheapest first
OpenAI · gpt-4.1-mini official price: not yet recorded. Cheapest inference provider: OpenRouter, input 0.4, output 1.6 USD per million tokens. Relays have only older quotes; the lowest is ai-api.loft.games, group "test" 0.336 CNY_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 96 sites have comparable prices; 173 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 | 0.4 | 1.6 | 0.1 | — | USD / 1M tokens | Official source |
Unit: CNY 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 ↑CNY credits / 1M | Output CNY credits / 1M | Cache readCNY credits / 1M | BlendedCNY credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Older price | |||||||
| 01 | openai-labs.comAsk or discussCollected: View 8 plans 1 more site of the same companyBasis: identical homepage assets, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | g1 OpenAI Lite | 0.2 | 0.8 | 0.05 | 0.35 | Full prices and sources |
| 02 | pro.gemai.ccAsk or discussCollected: View 3 plans | Azure All Azure group [machine translation]Original: Azure 分组 | 0.28 | 0.56 | 0.07 | 0.35 | Full prices and sources |
| 03 | ai.soruxgpt.comAsk or discussCollected: View 3 plans | azure-low Azure low-price group [machine translation]Original: Azure 低价分组 | 0.36 | 1.44 | 0.09 | 0.63 | Full prices and sources |
| 04 | i.v1api.ccAsk or discussCollected: View 3 plans | default Default group, supports all common models, 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，性价比首选，2折，倍率1.0 | 0.4 | 1.6 | — | 0.7 | Full prices and sources |
| 04 | www.ggwk1.onlineAsk or discussCollected: View 4 plans | a all-model combined group-1x rate multiplier [machine translation]Group on site: a全模型综合组-1倍率 a all-model combined group-1x rate multiplier [machine translation]Original: a全模型综合组-1倍率 | 0.4 | 1.6 | 0.1 | 0.7 | Full prices and sources |
| 06 | proaiapi.techAsk or discussCollected: View 2 plans | default Default group (for simple tasks, debugging, trial, personal learning, entry-level work tasks, etc.; low cost) [machine translation]Original: 默认分组 (适合简单任务、调试、体验、个人学习、初级工作任务等场景，成本低) | 0.416 | 1.664 | 0.104 | 0.728 | Full prices and sources |
| 07 | zhangsan.yunAsk or discussCollected: View 1 plans | image-2 group [machine translation]Group on site: image-2分组 image-2 image generation [machine translation]Original: image-2生图 | 0.45 | 1.8 | 0.1125 | 0.7875 | Full prices and sources |
| 08 | paw.v1chat.ccAsk or discussCollected: View 1 plans | default Standard channel, Gemini stability average, about 2.5/10 of the official price [machine translation]Original: 标准渠道，Gemini稳定性一般，约官方2.5折 | 0.5 | 2 | — | 0.875 | Full prices and sources |
| 09 | api.34ku.comAsk or discussCollected: View 1 plans | default Default group [machine translation]Original: 默认分组 | 0.52 | 2.08 | 0.13 | 0.91 | Full prices and sources |
| 10 | api.yanai.it.comAsk or discussCollected: View 1 plans | gpt_azure azure gpt, no image generation, has 5.5, no 5.6 [machine translation]Original: azure gpt，无生图，有 5.5，无 5.6 | 0.56 | 1.12 | 0.14 | 0.7 | Full prices and sources |
| 11 | us.ai.easyart.ccAsk or discussCollected: View 5 plans | gpt-cli gpt reverse-engineered [machine translation]Original: gpt逆向 | 0.6 | 2.4 | 0.15 | 1.05 | Full prices and sources |
| 12 | hboom.aiAsk or discussCollected: View 4 plans | Azure-Mid Azure-Mid | 0.816 | 3.264 | 0.204 | 1.428 | Full prices and sources |
| 13 | www.moxin.studioAsk or discussCollected: View 1 plans | GPT [boutique] [machine translation]Group on site: GPT[精品] GPT boutique, about 40% of official price [machine translation]Original: GPT精品 官方4折左右 | 1.2 | 2.4 | 0.3 | 1.5 | Full prices and sources |
| 13 | ai.astrumflow.comAsk or discussCollected: View 1 plans | Official relay OpenAI [machine translation]Group on site: 官转OpenAI Official relay OpenAI [machine translation]Original: 官转OpenAI | 1.2 | 4.8 | 0.3 | 2.1 | Full prices and sources |
| 13 | api.147ai.cnAsk or discussCollected: View 2 plans | az Azure key | OpenAl all models [machine translation]Original: Azure key | OpenAl全模型 | 1.2 | 4.8 | 0.3 | 2.1 | Full prices and sources |
| 16 | api.ccode.vipAsk or discussCollected: View 3 plans | OpenAi official KEY [machine translation]Group on site: OpenAi 官KEY OpenAi official KEY [machine translation]Original: OpenAi 官KEY | 1.96 | 8.11999999999972 | — | 3.49999999999993 | Full prices and sources |
| 17 | dapicloud.comAsk or discussCollected: View 1 plans | gpt-azure Microsoft official azure resources [machine translation]Original: 微软官方azure资源 | 4.8286548 | 9.6573096 | 1.2071637 | 6.0358185 | Full prices and sources |
| Flagged · not ranked · Older price | |||||||
| — | api.ccode.vipAsk or discussCollected: View 3 plans | OpenAi Azure forwarding [machine translation]Group on site: OpenAi Azure 转发 OpenAi Azure Forwarding - OpenAi Azure forwarding [machine translation]Original: OpenAi Azure Forwarding - OpenAi Azure 转发 Note: number precision issue. This price is not ranked or counted. | 0.728 | 3.015999999999896 | — | 1.299999999999974 | Full prices and sources |
| — | api.ccode.vipAsk or discussCollected: View 3 plans | OpenAi Azure full-strength [machine translation]Group on site: OpenAi Azure 满血 OpenAi Azure Full Blood - OpenAi Azure full-strength [machine translation]Original: OpenAi Azure Full Blood - OpenAi Azure 满血 Note: number precision issue. This price is not ranked or counted. | 0.896 | 3.711999999999872 | — | 1.599999999999968 | Full prices and sources |
Special groups · 1 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: 1 rows
- ai-api.loft.games · test · gpt-4.1-mini · Input 0.192 / Output 0.768 CNY 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 560 recorded prices; 280 can be compared directly (274 ranked, 6 listed separately). Not comparable yet: price not parsed yet 99, new price under review; showing the previous one 87, display unit not confirmed 32, tiered by rules (see Tiered prices) 25, scope of the official doc price not confirmed 24, ratio looks unset 7, billed per request or another unit 6
0 recent · 44 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.