LLM Releases
← Catalog

ERNIE 5.5 Flash Preview

Preview
BaiduProprietary

First post-trained model on ERNIE 5.5 Flash Base: a text-only 280B-total, 14B-active MoE with a 1M-token context, aimed at coding, 3D modeling, knowledge work and content creation. API on Baidu Qianfan; Baidu says weights will be open-sourced under Apache 2.0 later. An intermediate post-training checkpoint.

Specifications

License
Proprietary
Weights
Not released
Architecture
Mixture-of-Experts
Parameters
280B · 14B active
Context window
1.0M tokens
Max output
—
Knowledge cutoff
—
Price (in / out, $/M)
—
Modalities
TextCode

Benchmarks

No benchmark scores recorded yet. Spotted some? Submit a correction.

Vendor-reported figures are claims until independently verified. See methodology.