Understand this story
On November 11, 2026, Baidu Wenxin released ERNIE 5.5 Flash Preview and announced that the model is already available on OpenRouter and can be tried for free. On the same day, Arena announced that the model has entered Arena, where users can test it in Battle Mode with coding, web development, and real-world tasks; the Code Arena score will be announced later. Arena also mentioned that Baidu previously introduced the model as adopting a new architecture oriented toward efficient inference, with 280B total parameters, 14B activated per token, a 1M token context window, a generation speed exceeding 200 tokens/sec, and model weights to be released before November 25. On November 13, Baidu further stated that ERNIE 5.5 Flash Preview is an open-weight foundation model that can build playable worlds, 3D models, research reports, and interactive workbooks, among other things, and is already available on OpenRouter for direct trial.
AI-generated from public reports
Latest development · Report
Baidu Releases ERNIE 5.5 Flash Preview Open-Weight ModelDevelopments
4 confirmed developments
Baidu announces ERNIE 5.5 Flash Preview is available for trial on OpenRouter
Source:English text is being prepared.Baidu announces ERNIE 5.5 Flash Preview is available for trial on OpenRouter
Source:English text is being prepared.- Source:English text is being prepared.
- Source:Arena
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 13
BaiduFirst-partySelected
Baidu Releases ERNIE 5.5 Flash Preview Open-Weight Model
Baidu released ERNIE 5.5 Flash Preview, calling it an open-weight foundation model that can build playable worlds, 3D models, research reports, interactive workbooks, and more. The model is now available on OpenRouter and can be tried directly.
BaiduFirst-partySelected
Baidu Releases Open-Weight Model ERNIE 5.5 Flash Preview
Baidu has released the open-weight foundation model ERNIE 5.5 Flash Preview and made it available for trial on OpenRouter. The official examples cover generation tasks such as interactive worlds, 3D models, research reports, and interactive workbooks.
Nov 12
TMTPost · AGISelected
TMTPost Hands-On Test of Baidu ERNIE 5.5 Flash Preview: Coding Capability Greatly Improved, Open-Sourced on November 25
Baidu released its foundation model ERNIE 5.5 Flash Preview at the World Conference 2026. It adopts a sparse MoE architecture, with 280 billion total parameters and 14 billion activated, and supports a one-million-token long context. TMTPost conducted hands-on tests with four types of tasks: interactive web pages, game development, video production, and research report writing. Among them, generating an interactive page from a single sentence took 136.88 seconds and about 46,000 tokens, and a 32-page storage industry research report was completed in under 5 minutes. Official API pricing is 2 yuan per million input tokens during peak hours and 1 yuan during off-peak hours, and 8 yuan per million output tokens during peak hours and 4 yuan during off-peak hours. The model weights will be open-sourced under the Apache License 2.0 on November 25, and support deployment with SGLang and vLLM.
TMTPost · AGIRelated discussion
TMTPost · AGI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Leiphone
Baidu Releases ERNIE 5.5 Flash Preview, Focusing on Speed, Cost, and Open Source
Baidu has released ERNIE 5.5 Flash Preview, now available on the Qianfan platform, with both the web interface and API opened simultaneously; the model weights will be open-sourced under the Apache 2.0 license by November 25. The model has 280 billion total parameters and activates only 14 billion per token, and the Qianfan API delivers single-user inference speeds exceeding 200 tokens/s. API pricing is 2 yuan per million input tokens during peak hours and 1 yuan during off-peak hours, and 8 yuan per million output tokens during peak hours and 4 yuan during off-peak hours; a limited-time 50% discount is currently available, and deployment via SGLang and vLLM is supported.
BaiduFirst-party
Baidu Releases ERNIE 5.5 Flash Preview
Baidu announced that ERNIE 5.5 Flash Preview is ready and invited users to use it for their toughest tasks. Arena.ai stated that the model has entered the Arena and can be tested in Battle Mode on coding, web development, and real-world tasks, with Code Arena scores to be announced soon.
Nov 11
ArenaSelected
Baidu ERNIE 5.5 Flash Preview Launches in Arena Battle Mode
Arena announced that Baidu ERNIE 5.5 Flash Preview has entered Arena, where users can test the model in Battle Mode with coding, web development and real-world tasks; the Code Arena score will be announced later. Baidu previously said the model uses a new architecture designed for efficient inference, with 280B total parameters, 14B active per token, a 1M-token context window and a generation speed above 200 tokens/sec; the model weights will be released by November 25.
QbitAISelected
Baidu Releases ERNIE 5.5 Flash Preview, Focusing on End-to-End Programming and Announcing Imminent Open-Sourcing
Baidu released ERNIE 5.5 Flash Preview, with 280 billion total parameters and 14 billion activated per inference, supporting a million-token context and generating over 200 tokens per second, and announced it will soon be open-sourced. The model focuses on strengthening programming and Agent capabilities, and the company claims it can compete on par with Claude Opus 5.5 and GPT-6.1 Sol in benchmarks such as Terminal-Bench and AutomationBench. The author tested it by orchestrating animations with Python code, generating a playable "Backrooms" web game, and building a Suzhou garden in Blender. The weights are expected to be released soon under Apache 2.0 with support for SGLang and vLLM deployment; the API is already live on Baidu AI Cloud's Qianfan platform, with a limited-time 50% discount of 1 yuan for input and 4 yuan for output per million tokens.
BaiduFirst-party
Baidu ERNIE 5.5 Flash Preview Launches Free Trial on OpenRouter
Baidu announced that ERNIE 5.5 Flash Preview is now available on OpenRouter with a free trial.
IT Home · Artificial Intelligence
Baidu Wenxin releases the ERNIE 5.5 Flash Preview model, with open-source weights to be released before November 25
Baidu Wenxin has released ERNIE 5.5 Flash Preview, the first post-training version based on the previous Base model, with 280B total parameters, 14B activated parameters, and support for a 1M context. The model API is already available on the Qianfan platform, and the weights will be open-sourced before November 25. The official statement notes that this version is an intermediate version in the post-training process and may still have capability deficiencies caused by insufficient training; subsequent official versions will continue to be optimized.
LeiphoneSelected
Baidu Releases ERNIE 5.5 Flash Preview with 280 Billion Total Parameters and Support for a 1 Million Token Context
Baidu has released the foundation model ERNIE 5.5 Flash Preview, with 280 billion total parameters, 14 billion parameters activated per token, support for a context of up to 1 million tokens, and a generation speed exceeding 200 tokens per second. The model has undergone specialized training for scenarios such as programming, 3D modeling, knowledge work, and content creation, and has been launched on Baidu AI Cloud's Qianfan platform for developers to call via API. API pricing is 2 yuan per million input tokens during peak hours and 1 yuan during off-peak hours, and 8 yuan per million output tokens during peak hours and 4 yuan during off-peak hours, with a limited-time 50% discount. The model weights will be released to the global open-source community on November 25.
Heat trend for this story
- Current
- 8
- Period peak
- 50 Nov 12 06:00
- 24-hour change
- -49%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.