LLM Releases
← Catalog

DeepSeek V4-Flash

Preview
DeepSeekOpen source

Efficient V4 companion model with 284B total / 13B active parameters and the same one-million-token context window.

Specifications

License
Open source · MIT
Weights
Downloadable
Architecture
Mixture-of-Experts
Parameters
284B · 13B active
Context window
1M 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.