AIHubMixAIHubMix

Baidu Models

23 modelsGeneral models from $0.01/M inputUp to 183K context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

200M

Requests

50.9K

Models in use

22 of 23

Tokens per day

020.9M41.7M07-1307-2007-2708-0308-102026-07-13 — 41,744,145 tokens2026-07-14 — 27,744,535 tokens2026-07-15 — 876,355 tokens2026-07-16 — 3,267,295 tokens2026-07-17 — 3,678,200 tokens2026-07-18 — 1,237,760 tokens2026-07-19 — 2,142,770 tokens2026-07-20 — 963,625 tokens2026-07-21 — 1,657,435 tokens2026-07-22 — 1,097,760 tokens2026-07-23 — 1,015,420 tokens2026-07-24 — 411,075 tokens2026-07-25 — 839,205 tokens2026-07-26 — 92,045 tokens2026-07-27 — 772,635 tokens2026-07-28 — 2,283,405 tokens2026-07-29 — 1,789,530 tokens2026-07-30 — 3,037,980 tokens2026-07-31 — 1,622,600 tokens2026-08-01 — 1,836,640 tokens2026-08-02 — 331,495 tokens2026-08-03 — 387,770 tokens2026-08-04 — 3,912,845 tokens2026-08-05 — 1,176,285 tokens2026-08-06 — 8,263,035 tokens2026-08-07 — 21,705,650 tokens2026-08-08 — 17,853,355 tokens2026-08-09 — 5,151,735 tokens2026-08-10 — 24,355,700 tokens2026-08-11 — 18,490,420 tokens

Which models that traffic went to

  1. qianfan-ocr54.1%108M
  2. ernie-5.126.5%52.9M
  3. ernie-5.012.8%25.5M
  4. paddleocr-vl-0.9b5.0%10.1M
  5. ernie-5.0-thinking-preview1.1%2.2M
  6. ernie-x1.1-preview0.4%757K
  7. ernie-4.5-turbo-vl0.2%349K
  8. embedding-v1<0.1%5.5K
  9. 1 more model<0.1%5K

Share of 200M tokens. 13 models with traffic report no token counts and cannot be ranked here, including ernie-4.5-0.3b and ernie-4.5 — they are in the request view.

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 23 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 23 Baidu Models

Open in model list
Baidu 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
ernie-5.0-thinking-previewTakes text, returns text.183K64K$0.82$3.29/M$0.82/M72 tok/s6.53 s
ernie-4.5Takes text, vision, returns text.160K64K$0.07$0.27/M—99 tok/s0.95 s
ernie-4.5-turbo-vlTakes text, vision, returns text.139K16K$0.40$1.20/M—24 tok/s0.64 s
ernie-4.5-turbo-latestTakes text, vision, returns text.135K12K$0.11$0.44/M—18 tok/s0.62 s
ERNIE-X1.1-PreviewTakes text, returns text.119K64K$0.14$0.54/M—13 tok/s2.77 s
ernie-5.1Takes text, returns text.119K64K$0.56$2.54/M$0.56/M——
ernie-5.0Takes text, vision, audio, video, returns text.119K64K$0.82$3.29/M$0.82/M——
ernie-5.0-thinking-expTakes text, vision, returns text.119K64K$0.82$3.29/M$0.82/M——
ernie-x1-turboTakes text, returns text.51K28K$0.14$0.54/M—18 tok/s9.98 s
qianfan-ocrTakes text, vision, returns text.32K28K$0.06$0.25/M———
qianfan-ocr-fastTakes text, vision, returns text.32K28K$0.66$2.74/M———
paddleocr-vl-0.9bTakes , returns text.——Free$0.03/M———
pp-structurev3Takes , returns text.——Free$0.03/M———
ernie-4.5-0.3bTakes text, vision, returns text.——$0.01$0.05/M———
embedding-v1Takes text. Output modality not published.——$0.07$0.07/M———
tao-8k——$0.07$0.07/M———
ernie-4.5-turbo-128k-previewTakes text, vision, returns text.——$0.11$0.43/M———
ernie-x1.1-preview——$0.14$0.54/M—13 tok/s2.77 s
qianfan-qi-vl——$0.20$0.60/M———
baidu/ERNIE-4.5-300B-A47BTakes text, vision, returns text.——$0.32$1.28/M———
cc-ernie-4.5-300b-a47bTakes text, vision, returns text.——$0.32$1.28/M———
ernie-image-turboTakes , returns vision.——$2.00$2.00/M———
musesteamer-air-imageTakes , returns vision.——$2.00$2.00/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.

Common Comparisons

ERNIE-X1.1-Preview vs baidu/ERNIE-4.5-300B-A47BERNIE-X1.1-Preview vs cc-ernie-4.5-300b-a47bERNIE-X1.1-Preview vs ernie-4.5ERNIE-X1.1-Preview vs qwen3.8-max-previewERNIE-X1.1-Preview vs kimi-k3

Baidu on AIHubMix

Which Baidu model should I start with?

ernie-4.5-0.3b at $0.01/M input — the cheapest entry here that declares tool calling. Move up to ernie-image-turbo when answer quality matters more than cost, or to ernie-5.0-thinking-preview for long-form reasoning.

Which of these models reason before answering?

6 of the 23 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

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 (baidu/…), 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 Baidu 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 Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 models

Start calling Baidu in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect