API PRICES

OpenAI · text-embedding-3-large

Provider prices, cheapest first

Browse all models

OpenAI · text-embedding-3-large official price: not yet recorded. Relays have only older quotes; the lowest is zen-ai.top, group "free" 0.00013 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 85 sites have comparable prices; 142 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.

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

sites have comparable prices85142 sites list this model; approximately 53 operators
Older lowest input price (reference)0.02USD credits / 1M
Median of each provider’s lowest price0.13USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Older price
10yinli.oneAsk or discussCollected:
View 8 plans
deepseek
Deepseek channel [machine translation]Original: Deepseek渠道
0.130.13—0.13Full prices and sources
10zen-ai.topAsk or discussCollected:
View 3 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
0.130.13—0.13Full prices and sources
10api.zhiyunai168.comAsk or discussCollected:
View 4 plans
1 more site of the same company

Basis: 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
0.130.18571428571397—0.1439285714284925Full prices and sources
10codechn.comAsk or discussCollected:
View 2 plans
gpt/grok
Supported models: gpt, grok [machine translation]Original: 支持模型:gpt、grok
0.130.185714285713970.000928571428980.1439285714284925Full prices and sources
10new.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
0.130.185714285713970.000928571428980.1439285714284925Full prices and sources
31api.gravitex.aiAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
0.1430.143—0.143Full prices and sources
32hohoapi.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)
0.1690.169—0.169Full prices and sources
33learn-ai.topAsk or discussCollected:
View 1 plans
openai
1.5
0.1950.195—0.195Full prices and sources
33xrok.devAsk or discussCollected:
View 1 plans
AZ-GPT-1.3
AZ GPT supports high concurrency, channel 2 [machine translation]Original: AZ GPT支持高并发,渠道2
0.1950.195—0.195Full prices and sources
35api.eido.topAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
0.20.2—0.2Full prices and sources
36aws.babyAsk or discussCollected:
View 1 plans
Az GPT all [machine translation]Group on site: Az GPT 全
Azure GPT all models, supports oai image2.5 [machine translation]Original: Azure GPT 全模型 支持 oai image2.5
0.25870.36957142857080030.00184785714367020.286417857142700075Full prices and sources
37zzshu.ccAsk or discussCollected:
View 1 plans
Azure-GPT
Azure-GPT no distillation [machine translation]Original: Azure-GPT不可蒸馏
0.260.26—0.26Full prices and sources
38api.vibelearning.topAsk or discussCollected:
View 2 plans
azure-gpt
Independent official line, not a subscription-account reverse proxy, consistently stable, 2000 RPM, distillation allowed [machine translation]Original: 独立官方线路,非订阅账号反代,持续稳定,2000 RPM,可蒸馏
0.2860.286—0.286Full prices and sources
39api.xty.appAsk or discussCollected:
View 1 plans
1 more site of the same company

Basis: 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 group [machine translation]Original: 默认分组
0.390.55731—0.4318275Full prices and sources
40www.nuwaflux.comAsk or discussCollected:
View 2 plans
gpt-az select [machine translation]Group on site: gpt-az精品
All models covered, supports 1m context [machine translation]Original: 全模型覆盖支持1m上下文
0.4550.455—0.455Full prices and sources
41bikip.proAsk or discussCollected:
View 1 plans
default
default
0.50.5—0.5Full prices and sources
42www.amutes.comAsk or discussCollected:
View 1 plans
Openai pure official [machine translation]Group on site: Openai纯官
Openai pure official [machine translation]Original: Openai纯官
0.5460.546—0.546Full prices and sources
43www.cybersol.netAsk or discussCollected:
View 3 plans
Embeddings
Embeddings, Gemini, Openai official API direct connection. [machine translation]Original: Embeddings, Gemini, Openai 官方API直连。
0.60.6—0.6Full prices and sources
44a6api.comAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
11—1Full prices and sources
44api.wapq.cnAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
1111Full prices and sources
46api.aabao.topAsk or discussCollected:
View 1 plans
1 more site of the same company

Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

OpenAI direct connection [machine translation]Group on site: OpenAI直连
OpenAI direct connection (8.0x rate multiplier) [machine translation]Original: OpenAI直连(8.0倍率)
1.041.04—1.04Full prices and sources
Older price · Includes prices of 0 (free status unconfirmed)
— · Price of 0 · free status unconfirmedapi.pezayo.comAsk or discussCollected:
View 4 plans
coding anthropic
coding anthropic group, can only call kimi-latest, deepseek-flash models via the anthropic format [machine translation]Original: coding anthropic 分组,只能通过 anthropic 格式调用 kimi-latest,deepseek-flash 模型
0.0650—0.04875Full prices and sources
— · Price of 0 · free status unconfirmednewapi.prorisehub.comAsk or discussCollected:
View 2 plans
Embedding & Reranker
[Stability ⭐⭐⭐⭐⭐⭐] Embedding and Reranker model aggregated group, supports OpenAI / Voyage / Jina / Cohere / Qwen / BGE / Gemini / NVIDIA / ZeroEntropy and other mainstream vendors; the whole group is billed at a 0.2x rate multiplier [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐⭐】Embedding 嵌入与 Reranker 重排序模型聚合分组,支持 OpenAI / Voyage / Jina / Cohere / Qwen / BGE / Gemini / NVIDIA / ZeroEntropy 等主流厂商,全分组按 0.2x 倍率计费
0.06500.000464285714490.04875Full prices and sources
— · Price of 0 · free status unconfirmedgptapi.asiaAsk or discussCollected:
View 2 plans
2 more sites of the same company

Basis: 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 channel [machine translation]Original: 默认通道
0.1040—0.078Full prices and sources
— · Price of 0 · free status unconfirmedapi.luoqianyi.qzz.ioAsk or discussCollected:
View 1 plans
default
Default group [machine translation]Original: 默认分组
0.1300.000928571428980.0975Full prices and sources
Special groups · 8 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: 4 rows
  • near-zero-ratio group: 3 rows
  • internal or channel key: 1 rows
  • zen-ai.top · free · text-embedding-3-large · Input 0.00013 / Output 0.00013 USD credits / 1M
  • api.pezayo.com · codex anthropic · text-embedding-3-large · Input 0.000195 / Output 0 USD credits / 1M
  • api.pezayo.com · codex · text-embedding-3-large · Input 0.00195 / Output 0 USD credits / 1M
  • api.ai-gaochao.cn · test · text-embedding-3-large · Input 0.1 / Output 0.1 USD credits / 1M
  • new.yihubang.top · Company internal [machine translation]Group on site: 公司内部 · text-embedding-3-large · Input 0.13 / Output 0.18571428571397 USD credits / 1M
  • aigcbest.top · Test [machine translation]Group on site: 测试 · text-embedding-3-large · Input 0.455 / Output 0.455 USD credits / 1M
  • api.ifopen.ai · Test [machine translation]Group on site: 测试 · text-embedding-3-large · Input 0.455 / Output 0.455 USD credits / 1M
  • 35.aigcbest.top · Test [machine translation]Group on site: 测试 · text-embedding-3-large · Input 1.04 / Output 1.04 USD credits / 1M
View all 8 rows →
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 411 recorded prices; 236 can be compared directly (227 ranked, 9 listed separately). Not comparable yet: price not parsed yet 55, new price under review; showing the previous one 54, display unit not confirmed 28, scope of the official doc price not confirmed 24, tiered by rules (see Tiered prices) 14

0 recent · 191 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. 14 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.

Full methodology →

Switch model