BAAI Models

4 modelsGeneral models from $0.034/M input

Usage

Last 20 days · 2026-09-03 to 2026-10-02

Tokens

40M

Requests

34.4K

Models in use

4 of 4

Tokens per day, stacked by model

04.6M9.1M09-0309-1009-172026-09-03 — 7,530,235 tokens BAAI/bge-large-zh-v1.5: 7,522,565 BAAI/bge-large-en-v1.5: 6,890 bge-large-zh: 7802026-09-04 — 85,060 tokens 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 — 2,590,785 tokens BAAI/bge-large-zh-v1.5: 2,590,765 BAAI/bge-large-en-v1.5: 202026-09-06 — 4,971,780 tokens BAAI/bge-large-zh-v1.5: 4,971,750 BAAI/bge-large-en-v1.5: 302026-09-07 — 215,835 tokens BAAI/bge-large-zh-v1.5: 201,165 bge-large-zh: 14,6702026-09-08 — 3,845,020 tokens BAAI/bge-large-zh-v1.5: 3,845,005 BAAI/bge-large-en-v1.5: 152026-09-09 — 1,557,525 tokens BAAI/bge-large-zh-v1.5: 1,556,620 bge-large-zh: 9052026-09-10 — 1,578,295 tokens BAAI/bge-large-zh-v1.5: 1,578,265 BAAI/bge-large-en-v1.5: 302026-09-11 — 9,106,675 tokens BAAI/bge-large-zh-v1.5: 9,106,645 BAAI/bge-large-en-v1.5: 302026-09-12 — 1,261,620 tokens BAAI/bge-large-zh-v1.5: 1,261,605 BAAI/bge-large-en-v1.5: 152026-09-13 — 820,330 tokens BAAI/bge-large-zh-v1.5: 820,325 bge-large-zh: 52026-09-14 — 476,130 tokens BAAI/bge-large-zh-v1.5: 476,1302026-09-15 — 2,198,270 tokens BAAI/bge-large-zh-v1.5: 2,198,2702026-09-16 — 1,396,175 tokens BAAI/bge-large-zh-v1.5: 1,396,1752026-09-17 — 1,742,055 tokens bge-large-zh: 1,187,235 bge-large-en: 441,850 BAAI/bge-large-zh-v1.5: 112,9702026-09-18 — 5,110 tokens bge-large-en: 5,1102026-09-22 — 3,240 tokens bge-large-en: 3,2402026-09-28 — 12,075 tokens bge-large-zh: 12,0752026-09-29 — 100 tokens bge-large-zh: 1002026-10-02 — 646,390 tokens bge-large-zh: 646,390
  • BAAI/bge-large-zh-v1.5
  • bge-large-zh
  • bge-large-en
  • BAAI/bge-large-en-v1.5

Which models that traffic went to

  1. BAAI/bge-large-zh-v1.594.2%37.7M
  2. Bge Large Zh4.7%1.9M
  3. Bge Large En1.1%450K
  4. BAAI/bge-large-en-v1.5<0.1%7.1K

Share of 40M 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 20 days, counting the 4 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 4 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
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
149 modelsOpenAI
142 modelsGoogle
87 modelsZ.AI
71 modelsLlama
53 models

Start calling BAAI in one line

One key, one endpoint, 911 models across 42 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies