API PRICES
OpenAI · text-embedding-3-small
Provider prices, cheapest first
All official and inference price observations
OpenAI · text-embedding-3-small official price: not yet recorded. Cheapest relay: yinli.one, group "deepseek" 0.02 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-11-13). 123 sites have comparable prices; 210 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Relay USD credit prices · Lowest 0.02 · median 0.035 · highest 0.1 · 8 quotes USD / per million tokens, site credit
Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.
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.
Price range: lowest 0.02 · median 0.035 · highest 0.1 (8 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 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | deepseek Deepseek channel [machine translation]Original: Deepseek渠道 Operator pending verification | 0.02 | 0.02 | — | 0.02The median price is 1.8× this price | Details |
| 02 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | Claude-Kior-low price-90% stability [machine translation]Group on site: Claude-Kior-低价-90%稳定性 Mainly for model distillation, must use the openai official relay channel, streaming first token 1-3s [machine translation]Original: 主要用于模型蒸馏,一定需要用openai官转渠道,流式输出首字1-3s Operator pending verification | 0.03 | 0.03 | — | 0.03The median price is 1.2× this price | Details |
| 02 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | GPT-Azure-low price-90% stability [machine translation]Group on site: GPT-Azure-低价-90%稳定性 Personal use/small experiments/model distillation, streaming first token 5-10s [machine translation]Original: 个人使用/小型实验使用/模型蒸馏使用,流式输出首字5-10s Operator pending verification | 0.03 | 0.03 | — | 0.03The median price is 1.2× this price | Details |
| 02 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | Gemini-low price-90% stability [machine translation]Group on site: Gemini-低价-90%稳定性 Personal use/small experiments/claude code, streaming first token 3-5s [machine translation]Original: 个人使用/小型实验使用/claude code,流式输出首字3-5s Operator pending verification | 0.03 | 0.03 | — | 0.03The median price is 1.2× this price | Details |
| 05 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | Model aggregated group stability 90% [machine translation]Group on site: 模型聚合分组稳定性90% claude, gpt, deepseek, gemini available channel [machine translation]Original: claude、gpt、deepseek、gemini可用渠道 Operator pending verification | 0.04 | 0.04 | — | 0.041.1× the median price | Details |
| 06 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | GPT-Azure-mid price-95% stability [machine translation]Group on site: GPT-Azure-中价-95%稳定性 Personal use/small experiments/model distillation, streaming first token 5-10s [machine translation]Original: 个人使用/小型实验使用/模型蒸馏使用,流式输出首字5-10s Operator pending verification | 0.06 | 0.06 | — | 0.061.7× the median price | Details |
| 07 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | GPT-Azure-high price-99% stability [machine translation]Group on site: GPT-Azure-高价-99%稳定性 Personal use/small experiments/commercial APP use, streaming first token 3-5s [machine translation]Original: 个人使用/小型实验使用/商业APP使用,流式输出首字3-5s Operator pending verification | 0.1 | 0.1 | — | 0.12.9× the median price | Details |
| 07 | yinli.oneAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 8 plans | GPT-openai official relay-high price-95% stability [machine translation]Group on site: GPT-openai官转-高价-95%稳定性 Commercial APP use, recommended when stability needs are very high, streaming first token 1-3s [machine translation]Original: 商业APP使用,稳定性要求极高推荐使用,流式输出 首字1-3s Operator pending verification | 0.1 | 0.1 | — | 0.12.9× the median price | Details |
Special groups · 3 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: 2 rows
- test or debug group: 1 rows
- api.pezayo.com · codex anthropic · text-embedding-3-small · Input 0.00003 / Output 0 USD credits / 1M
- api.pezayo.com · codex · text-embedding-3-small · Input 0.0003 / Output 0 USD credits / 1M
- test-api.apiqik.online · openai · text-embedding-3-small · Input 0.006 / Output 0.006 USD credits / 1M
How this ranking works
All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.
This model has 555 recorded prices; 298 can be compared directly (295 ranked, 3 listed separately). Not comparable yet: price not parsed yet 172, scope of the official doc price not confirmed 24, display unit not confirmed 8, new price under review; showing the previous one 4, ratio looks unset 3, billed per request or another unit 2. 31 more are tiered by rules and compared on the Tiered prices board
8 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.
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 · text-embedding-3-small?
yinli.one, group "deepseek", 0.02 USD credit per million total tokens, observed 2026-11-13. 123 sites have comparable prices.
How do I use OpenAI · text-embedding-3-small in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest OpenAI · text-embedding-3-small API to Claude Code for me". Install Skill →