AIHubMixAIHubMix

BAAI Models

5 modelsGeneral models from $0.034/M input

Usage

Last 30 days · 2026-08-09 to 2026-09-07

Tokens

32.8B

Requests

1.3M

Models in use

5 of 5

Tokens per day, stacked by model

0750M1.5B08-0908-1608-2308-3009-062026-08-09 — 1,063,360,220 tokens BAAI/bge-reranker-v2-m3: 1,038,684,470 BAAI/bge-large-en-v1.5: 24,646,760 BAAI/bge-large-zh-v1.5: 28,870 bge-large-zh: 1202026-08-10 — 1,261,013,440 tokens BAAI/bge-reranker-v2-m3: 1,261,013,335 BAAI/bge-large-zh-v1.5: 90 BAAI/bge-large-en-v1.5: 152026-08-11 — 1,117,089,765 tokens BAAI/bge-reranker-v2-m3: 1,114,567,230 bge-large-zh: 2,517,590 BAAI/bge-large-zh-v1.5: 4,9452026-08-12 — 781,810,540 tokens BAAI/bge-reranker-v2-m3: 780,063,905 BAAI/bge-large-zh-v1.5: 1,746,6352026-08-13 — 749,362,230 tokens BAAI/bge-reranker-v2-m3: 749,351,845 BAAI/bge-large-zh-v1.5: 5,975 bge-large-zh: 2,445 BAAI/bge-large-en-v1.5: 1,9652026-08-14 — 623,179,655 tokens BAAI/bge-reranker-v2-m3: 623,173,160 BAAI/bge-large-zh-v1.5: 4,815 bge-large-zh: 1,6802026-08-15 — 584,617,145 tokens BAAI/bge-reranker-v2-m3: 584,616,140 BAAI/bge-large-zh-v1.5: 990 BAAI/bge-large-en-v1.5: 152026-08-16 — 533,563,845 tokens BAAI/bge-reranker-v2-m3: 526,591,140 BAAI/bge-large-zh-v1.5: 6,954,635 bge-large-zh: 17,985 BAAI/bge-large-en-v1.5: 60 bge-large-en: 252026-08-17 — 451,008,250 tokens BAAI/bge-reranker-v2-m3: 450,640,385 BAAI/bge-large-zh-v1.5: 367,850 BAAI/bge-large-en-v1.5: 152026-08-18 — 821,141,530 tokens BAAI/bge-reranker-v2-m3: 821,082,025 BAAI/bge-large-zh-v1.5: 49,480 bge-large-zh: 10,010 BAAI/bge-large-en-v1.5: 152026-08-19 — 1,182,379,165 tokens BAAI/bge-reranker-v2-m3: 1,182,244,805 BAAI/bge-large-en-v1.5: 125,160 BAAI/bge-large-zh-v1.5: 9,2002026-08-20 — 1,279,015,410 tokens BAAI/bge-reranker-v2-m3: 1,274,933,250 BAAI/bge-large-zh-v1.5: 3,922,040 bge-large-zh: 160,1202026-08-21 — 1,366,224,875 tokens BAAI/bge-reranker-v2-m3: 1,365,980,095 BAAI/bge-large-zh-v1.5: 236,970 bge-large-zh: 7,8102026-08-22 — 1,242,711,140 tokens BAAI/bge-reranker-v2-m3: 1,238,906,080 BAAI/bge-large-zh-v1.5: 3,805,0602026-08-23 — 1,214,791,425 tokens BAAI/bge-reranker-v2-m3: 1,214,701,625 BAAI/bge-large-zh-v1.5: 71,270 bge-large-zh: 18,5302026-08-24 — 1,492,384,010 tokens BAAI/bge-reranker-v2-m3: 1,491,985,850 BAAI/bge-large-zh-v1.5: 398,145 BAAI/bge-large-en-v1.5: 152026-08-25 — 1,499,572,825 tokens BAAI/bge-reranker-v2-m3: 1,499,134,065 BAAI/bge-large-zh-v1.5: 438,7602026-08-26 — 1,316,507,355 tokens BAAI/bge-reranker-v2-m3: 1,316,364,855 BAAI/bge-large-zh-v1.5: 142,345 BAAI/bge-large-en-v1.5: 135 bge-large-zh: 10 bge-large-en: 102026-08-27 — 1,236,794,090 tokens BAAI/bge-reranker-v2-m3: 1,236,687,290 BAAI/bge-large-zh-v1.5: 106,8002026-08-28 — 1,170,490,130 tokens BAAI/bge-reranker-v2-m3: 1,169,626,140 BAAI/bge-large-zh-v1.5: 674,280 BAAI/bge-large-en-v1.5: 189,7102026-08-29 — 981,268,020 tokens BAAI/bge-reranker-v2-m3: 981,113,905 BAAI/bge-large-zh-v1.5: 149,830 bge-large-zh: 2,265 BAAI/bge-large-en-v1.5: 2,0202026-08-30 — 932,448,550 tokens BAAI/bge-reranker-v2-m3: 931,600,085 BAAI/bge-large-zh-v1.5: 837,920 BAAI/bge-large-en-v1.5: 10,5452026-08-31 — 1,037,624,775 tokens BAAI/bge-reranker-v2-m3: 1,037,019,840 BAAI/bge-large-zh-v1.5: 604,905 BAAI/bge-large-en-v1.5: 302026-09-01 — 1,185,273,260 tokens BAAI/bge-reranker-v2-m3: 1,184,932,360 BAAI/bge-large-zh-v1.5: 340,885 BAAI/bge-large-en-v1.5: 152026-09-02 — 1,347,211,080 tokens BAAI/bge-reranker-v2-m3: 1,346,576,485 BAAI/bge-large-zh-v1.5: 634,5952026-09-03 — 1,397,081,730 tokens BAAI/bge-reranker-v2-m3: 1,389,551,495 BAAI/bge-large-zh-v1.5: 7,522,565 BAAI/bge-large-en-v1.5: 6,890 bge-large-zh: 7802026-09-04 — 1,460,019,665 tokens BAAI/bge-reranker-v2-m3: 1,459,934,605 BAAI/bge-large-zh-v1.5: 84,985 BAAI/bge-large-en-v1.5: 30 bge-large-en: 25 bge-large-zh: 202026-09-05 — 1,165,197,810 tokens BAAI/bge-reranker-v2-m3: 1,162,607,025 BAAI/bge-large-zh-v1.5: 2,590,765 BAAI/bge-large-en-v1.5: 202026-09-06 — 1,100,004,190 tokens BAAI/bge-reranker-v2-m3: 1,095,032,410 BAAI/bge-large-zh-v1.5: 4,971,750 BAAI/bge-large-en-v1.5: 302026-09-07 — 1,214,182,795 tokens BAAI/bge-reranker-v2-m3: 1,213,966,960 BAAI/bge-large-zh-v1.5: 201,165 bge-large-zh: 14,670
  • BAAI/bge-reranker-v2-m3
  • BAAI/bge-large-zh-v1.5
  • BAAI/bge-large-en-v1.5
  • bge-large-zh
  • bge-large-en

Which models that traffic went to

  1. BAAI/bge-reranker-v2-m399.8%32.7B
  2. BAAI/bge-large-zh-v1.50.1%36.9M
  3. BAAI/bge-large-en-v1.50.1%25M
  4. Bge Large Zh<0.1%2.8M
  5. Bge Large En<0.1%60

Share of 32.8B tokens.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 5 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 5 BAAI Models

Open in model list
BAAI models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
BAAI/bge-large-en-v1.5Takes text, vision. Output modality not published.$0.034$0.034/M
BAAI/bge-large-zh-v1.5Takes text, vision. Output modality not published.$0.034$0.034/M
BAAI/bge-reranker-v2-m3Takes text, vision. Output modality not published.$0.034$0.034/M
bge-large-enTakes text, vision. Output modality not published.$0.068$0.068/M
bge-large-zhTakes text, vision. Output modality not published.$0.068$0.068/M

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

BAAI on AIHubMix

Which BAAI model should I start with?

BAAI/bge-large-en-v1.5 at $0.034/M input — the cheapest entry here that declares tool calling. Move up to bge-large-en when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (BAAI/…), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

Do I need a separate BAAI account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
144 modelsOpenAI
134 modelsGoogle
85 modelsZ.AI
71 modelsLlama
53 models

Start calling BAAI in one line

One key, one endpoint, 880 models across 38 model authors.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect