Baidu models
Chinese internet and AI company that develops the ERNIE foundation model family, the ERNIE assistant app, the PaddlePaddle framework, and the Qianfan model platform.
Beijing, ChinaFounded 2000baidu.com
- Releases
- 21
- Open weights
- 11
- Latest
- Nov 11, 2026
November 2026
2 releasesERNIE 5.5 Flash Preview
ERNIE 5.5 Flash Preview is the first post-trained model built on ERNIE 5.5 Flash Base, released as an intermediate checkpoint while Baidu's post-training continued. At launch it was offered through Baidu's Qianfan API, with weights promised later.
- Modalities
- text → text
- Context
- 1M context
- Parameters
- MoE: 280B total, 14B active
- At launch
- API
- Intermediate post-training checkpoint of the ERNIE 5.5 Flash Base mixture-of-experts model
- 280B total and 14B active parameters with a 1M-token context
- API on Baidu's Qianfan platform at launch, plus a free OpenRouter listing linked from the announcement
- Baidu said at launch that the weights would be open-sourced under Apache 2.0 at a later date
ERNIE 5.5 Flash Base
ERNIE 5.5 Flash Base is the open-weights pre-training checkpoint of Baidu's sparse mixture-of-experts ERNIE 5.5 Flash model, released before any mid- or post-training as a starting point for fine-tuning and reinforcement learning research.
- Modalities
- text → text
- Context
- 1M context
- Parameters
- MoE: 280B total, 14B active
- License
- ERNIE 5.5 Flash Base Model License Agreement v1.0
- At launch
- Open weights
- Pre-trained from scratch on 33.5T tokens with training context up to 128K; fine-tuning and inference support a 1M-token context
- Hybrid attention plus a latent MoE layer with 512 routed experts (top-10) and one shared expert
- FP8 and BF16 weights on Hugging Face, with serving support in SGLang and vLLM
- Baidu says the post-trained ERNIE 5.5 Flash will follow
October 2026
1 releaseUnlimited-OCR 2
Unlimited-OCR 2 is Baidu's second-generation open document-parsing vision-language model, adding Sparse Reference Sliding Window Attention so it can parse documents of unbounded length within a finite context window.
- Modalities
- image, text → text
- License
- MIT
- At launch
- Open weights, API
- SR-SWA compresses text-visual attention from ultra-long sequences to a fixed set of working references, such as 512 tokens
- Supports multi-page inference that parses all pages of a document in one request
- Released with the MarathonDocBench ultra-long document benchmark; also offered on Baidu Cloud
- Supports Transformers and SGLang serving
June 2026
1 releaseUnlimited-OCR
Unlimited-OCR is an open vision-language OCR model from Baidu aimed at one-shot, long-horizon parsing of documents, which Baidu describes as pushing the DeepSeek-OCR approach one step further.
- Modalities
- image, text → text
- License
- MIT
- At launch
- Open weights, API
- Weights on Hugging Face and ModelScope under the MIT license
- vLLM inference support added June 28, 2026
- Made available on Baidu Cloud on July 3, 2026
May 2026
1 releaseERNIE 5.1
ERNIE 5.1 is Baidu's successor to ERNIE 5.0, derived through an elastic training framework that compresses total parameters to about one-third and active parameters to about one-half of ERNIE 5.0.
- Modalities
- text → text
- At launch
- Consumer app
- Four-stage post-training that includes multi-teacher on-policy distillation and online reinforcement learning
- Available on the ERNIE website and in an ERNIE 5.1 playground on Baidu AI Studio
April 2026
1 releaseERNIE-Image
ERNIE-Image is Baidu's open text-to-image model, built on a single-stream Diffusion Transformer with a lightweight Prompt Enhancer, and released alongside a distilled ERNIE-Image-Turbo variant for faster generation.
- Modalities
- text → image
- Parameters
- 8B
- License
- Apache-2.0
- At launch
- Open weights
- 8B DiT parameters; runs on consumer GPUs with 24GB of VRAM
- ERNIE-Image uses about 50 inference steps; ERNIE-Image-Turbo uses 8 steps after DMD and RL optimization
- Targets dense text rendering, posters, comics, and multi-panel layouts
March 2026
1 releaseQianfan-OCR
Qianfan-OCR is a 4B end-to-end document intelligence model from Baidu's Qianfan team that unifies document parsing, layout analysis, table and formula recognition, chart understanding, and key information extraction in one model.
- Modalities
- image, text → text
- Parameters
- 4B
- License
- Apache-2.0
- At launch
- Open weights
- Optional Layout-as-Thought phase reasons about bounding boxes, element types, and reading order before output
- Language model based on Qwen3-4B with 32K context, extendable to 131K
- Supports 192 languages
- Trained on 1,024 Kunlun P800 chips
January 2026
1 releasePaddleOCR-VL-1.5
PaddleOCR-VL-1.5 updates Baidu's 0.9B document-parsing vision-language model for in-the-wild robustness, handling skewed, warped, and photographed pages, and adds text spotting and seal recognition.
- Modalities
- image, text → text
- Parameters
- 0.9B
- License
- Apache-2.0
- At launch
- Open weights
- Supports irregular-shaped (polygon) localization for distorted documents
- Adds automatic cross-page table merging and cross-page heading recognition
- Language coverage adds Tibetan and Bengali
November 2025
2 releasesERNIE 5.0
ERNIE 5.0 is Baidu's natively omni-modal foundation model that jointly models text, images, audio, and video in a unified autoregressive framework for both understanding and generation. Baidu unveiled a preview at Baidu World 2025.
- Modalities
- text, image, audio, video → text, image, audio, video
- Parameters
- MoE: 2.4T total, about 3% active per token
- At launch
- Consumer app, API
- Preview offered through ERNIE Bot and Baidu AI Cloud's Qianfan platform at announcement
- Official version launched January 22, 2026, with 2.4 trillion parameters
- Mixture-of-experts design that activates about 3% of parameters per token
ERNIE-4.5-VL-28B-A3B-Thinking
ERNIE-4.5-VL-28B-A3B-Thinking is an open-weights multimodal reasoning upgrade of ERNIE-4.5-VL-28B-A3B, adding extended mid-training, reinforcement learning, and thinking with images that zooms into regions and calls image search.
- Modalities
- text, image, video → text
- Parameters
- MoE: 28B total, 3B active
- License
- Apache-2.0
- At launch
- Open weights
- Activates 3B parameters per token
- Strengthened visual grounding plus video temporal awareness and event localization
- Weights on Hugging Face; runs with transformers, vLLM, and FastDeploy
October 2025
1 releasePaddleOCR-VL
PaddleOCR-VL is Baidu's open document-parsing system built around PaddleOCR-VL-0.9B, a compact vision-language model that pairs a NaViT-style dynamic-resolution visual encoder with the ERNIE-4.5-0.3B language model.
- Modalities
- image, text → text
- Parameters
- 0.9B
- License
- Apache-2.0
- At launch
- Open weights
- Supports 109 languages
- Recognizes text, tables, formulas, and charts, including handwriting and historical documents
- Uses PP-DocLayoutV2 for layout analysis and reading order, with Markdown and JSON output
September 2025
3 releasesQianfan-VL
Qianfan-VL is a Baidu AI Cloud family of vision-language models in 3B, 8B, and 70B sizes, continuously pre-trained for enterprise OCR and document understanding, with chain-of-thought reasoning in the 8B and 70B versions.
- Modalities
- image, text → text
- Context
- 32K context
- Parameters
- 3B, 8B, 70B
- License
- MIT
- At launch
- Open weights
- 3B model built on Qwen2.5-3B; 8B and 70B models based on the Llama 3.1 architecture
- InternViT-based vision encoder with dynamic patching up to 4K resolution
- 32K context across all three sizes
ERNIE X1.1
ERNIE X1.1 upgrades Baidu's ERNIE X1 deep-thinking model, using an iterative hybrid reinforcement learning framework to improve factuality, instruction following, and agentic task performance.
- Modalities
- text → text
- At launch
- Consumer app, API
- Announced at WAVE SUMMIT 2025
- Available on the ERNIE Bot website, the Wenxiaoyan app, and Baidu AI Cloud Qianfan
- Like ERNIE X1, trained from ERNIE 4.5
ERNIE-4.5-21B-A3B-Thinking
ERNIE-4.5-21B-A3B-Thinking is an open-weights deep-thinking model trained from ERNIE-4.5-21B-A3B for reasoning, math, code, and tool use, released in Transformer-style weights for PyTorch and PaddlePaddle tooling.
- Modalities
- text → text
- Context
- 128K context
- Parameters
- MoE: 21B total, 3B active
- License
- Apache-2.0
- At launch
- Open weights
- Open-sourced at WAVE SUMMIT 2025 on September 9, 2025
- Enhanced 128K long-context understanding
- Runs with vLLM, transformers, and FastDeploy
June 2025
1 releaseERNIE 4.5 (open-weight family)
Baidu open-sourced the ERNIE 4.5 family of 10 variants: mixture-of-experts language and vision-language models with 47B or 3B active parameters plus a 0.3B dense model, trained with PaddlePaddle and offered in PyTorch-compatible formats.
- Modalities
- text, image → text
- Context
- 128K context
- Parameters
- MoE: up to 424B total, 47B active; plus a 0.3B dense model
- License
- Apache-2.0
- At launch
- Open weights
- Largest models are ERNIE-4.5-300B-A47B (text) and ERNIE-4.5-VL-424B-A47B (vision-language)
- 131,072-token context length per the Hugging Face model cards
- Vision-language models support thinking and non-thinking modes
- Released with the ERNIEKit fine-tuning and FastDeploy deployment toolkits
April 2025
2 releasesERNIE 4.5 Turbo
ERNIE 4.5 Turbo is a faster multimodal model derived from ERNIE 4.5, launched at Baidu Create 2025 with improvements in hallucination reduction, logical reasoning, and coding.
- Modalities
- text, image, video → text
- At launch
- API
- Launched at Baidu Create 2025 in Wuhan
- Enhanced multimodal capabilities, launched alongside ERNIE X1 Turbo
- Serves as the base for the ERNIE X1 Turbo reasoning model
ERNIE X1 Turbo
ERNIE X1 Turbo is a deep-thinking model built on ERNIE 4.5 Turbo, launched at Baidu Create 2025 with a more advanced chain of thought and stronger question answering, writing, reasoning, tool use, and multimodal abilities.
- Modalities
- text, image → text
- At launch
- API
- Launched with ERNIE 4.5 Turbo at Create 2025 in Wuhan
- Combines thinking with tool calls in a compound chain of thought and action
- Built on ERNIE 4.5 Turbo, which is derived from ERNIE 4.5
March 2025
2 releasesERNIE 4.5
ERNIE 4.5 is Baidu's new-generation native multimodal foundation model, jointly modeling text, images, audio, and video, with stronger language understanding, generation, logic, and memory and reduced hallucination.
- Modalities
- text, image, audio, video → text
- At launch
- Consumer app, API
- Free on the ERNIE Bot website at launch
- API available to enterprises and developers on Baidu AI Cloud Qianfan
- Uses FlashMask dynamic attention masking and heterogeneous multimodal experts
ERNIE X1
ERNIE X1 is Baidu's deep-thinking reasoning model, released with ERNIE 4.5 and described as the first deep-thinking model to use tools autonomously, including search, document Q&A, image understanding, and a code interpreter.
- Modalities
- text, image → text
- At launch
- Consumer app
- Free to users on the ERNIE Bot website at launch
- Qianfan API availability announced as coming soon
- Trained with progressive reinforcement learning and end-to-end chain-of-thought and action training
October 2023
1 releaseERNIE 4.0
ERNIE 4.0 is Baidu's next-generation foundation model, unveiled at Baidu World 2023 with upgrades in understanding, generation, reasoning, and memory, and used to power a new version of ERNIE Bot.
- Modalities
- text → text
- At launch
- Consumer app, API
- Beta testing began in September 2023, before the launch
- Accessible to invited users on ERNIE Bot at launch
- Enterprise API testing offered through the Qianfan foundation model platform
March 2023
1 releaseERNIE Bot
ERNIE Bot is Baidu's large language model and generative AI product, launched with abilities in literary creation, business writing, mathematical calculation, Chinese language understanding, and multimodal generation.
- Modalities
- text → text, image, audio, video
- At launch
- Consumer app, API
- Opened to invited users with invitation codes on March 16, 2023
- Enterprise API access offered on application through Baidu AI Cloud
- Baidu demonstrated generation of text, images, audio, and video from text prompts
Cite and reuse this data
These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL.
Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".
Citation
The AI Engineering Editors. "Baidu models: release history and timeline." The AI Engineering, updated Nov 11, 2026. https://theaiengineering.com/releases/baidu
HTML link
<a href="https://theaiengineering.com/releases/baidu">Baidu models: release history and timeline</a> (The AI Engineering)- Full dataset
- 1,167 releases from 55 labs
- Coverage
- to
- Updated
- License
- CC BY 4.0
- Publisher
- The AI Engineering
Other labs
Google106
Alibaba Qwen84
OpenAI79Mistral AI59
Meta44
- Z.ai43
Microsoft42Tencent42
- ByteDance Seed40
- DeepSeek38
- Liquid AI34
Cohere31- IBM30
xAI30- NVIDIA29
MiniMax28
Stability AI28- Anthropic26
Ai223StepFun22
Amazon21- ElevenLabs21
Black Forest Labs18
- Kuaishou16
- Meituan16
Runway16- Moonshot AI15
Midjourney14Salesforce13
- Xiaomi13
Nous Research11- Perplexity10
AI21 Labs8- Apple8
Ideogram8
01.AI7
Hugging Face7
Lightricks7Luma AI7
Reka7- Suno7
- Databricks5
Leonardo.Ai5- Pika5
Recraft5
Inflection AI3MBZUAI IFM3
- Snowflake3
Thinking Machines Lab3
TypeSafe AI2- Cognition1
Genmo1Reflection AI1
Ricursive Intelligence1