- input
- $0.00
- output
- $0.00
- Context
- 262Ktokens
- Listed
- Today
- Size
- 4.5Bparameters
Cost/1M tokens
Language model from Perplexity, listed on OpenRouter on November 12, 2026.
- Decision model
- Open weights · 4.5B
- Accepts images
How it compares
Frequently asked questions
Running locally
By our estimate, Decider Flash V1.3 needs about 3.7 GB at Q4, 6 GB at Q8 and 10.9 GB at FP16 of VRAM. That covers the weights plus headroom for a short context, and longer contexts need more.
Yes, by our estimates Decider Flash V1.3 fits on an 8 GB GPU at Q8 (about 6 GB) and at higher precision on larger cards.
Yes, a Mac with at least 8 GB of unified memory should run Decider Flash V1.3 at Q4, which needs an estimated 3.7 GB. This assumes macOS gives the GPU about 75% of unified memory.
Privacy and data
Yes, Decider Flash V1.3 has open weights, so you can run it on your own hardware and keep prompts on your own machines.
Capabilities and specs
Decider Flash V1.3 has a 262K token context window. It can write up to 236K output tokens per response.
Yes, Decider Flash V1.3 accepts images as input alongside text.
Quality and benchmarks
Similar models from other labs include Span-01 Lite (Respan), Decisions Fast (Parallel) and Span-02 (Respan). They are the closest matches by kind and release date.
Span-01 LiteDecider Flash V1.3 vs Span-01 LiteDecisions FastDecider Flash V1.3 vs Decisions FastSpan-02Decider Flash V1.3 vs Span-02
Licensing and access
Decider Flash V1.3 has open weights, so you can download and run it yourself.
The Decider Flash V1.3 weights are on Hugging Face at perplexity-ai/pplx-decider-flash-v1.3.
Basics
Decider Flash V1.3 was made by Perplexity. It was first listed on OpenRouter on November 12, 2026.
Yes, Decider Flash V1.3 has open weights, so you can run it on your own hardware without API fees.
Generated from Vertical Tabs data, updated November 12, 2026.
Discussion
No comments yet
Be the first to share your thoughts.