perplexity
Perplexity: Decider Flash V1.2
perplexity/pplx-decider-flash-v1.2
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Perplexity’s Decider Flash V1.2 is a compact decision model documented as a distilled, smaller sibling of Decider V1.2, sharing the same request format and API while accepting text and images. It emits structured answers for multiple-choice, Boolean-style, and ordered-score questions rather than generating prose. Vendor evaluations report lower measured decision quality than the larger model but better efficiency; independent evidence remains limited, so workload validation is advised.[1][2]
Strengths
- Accepts text and image inputs through the same joint request format and API contract as the larger Decider.[1][2]
- Supports discrete choices, binary probabilities, and ordered scores, with probabilities or confidence where applicable and access to raw logits.[2]
- The documentation positions the distilled checkpoint for latency- or cost-sensitive deployments while reporting that it retains much of the larger model’s measured decision quality.[2]
Limitations
- It returns decision objects rather than prose, so open-ended drafting or explanation requires another component.[1][2]
- Detailed evidence is primarily vendor documentation; OpenRouter’s benchmark fields are unset in this pack, so independent task validation remains necessary.[1][2]
- Sequences beyond the documented training length were only spot-checked, and deployment requires private repository access, CUDA-capable hardware, and a serving path that supports its noncausal layers and per-marker readout.[2]
Where to use it
- Possible fit for support or operations triage that assigns team, urgency, and sentiment-style labels from one shared state.[2]
- May suit selection or ranking workflows that benefit from probabilities or binary logit margins rather than generated rationales.[2]
- Could be considered for decision tasks that combine text context with images, after checking the documented image and sequence limits.[1][2]
Sources
- [1] OpenRouter catalog · Perplexity: Decider Flash V1.2Sources checked: Nov 13, 2026
- [2] Model documentation · Perplexity: Decider Flash V1.2Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Decider Flash V1.2 is a 4B-parameter decision model from Perplexity, a smaller, lower-cost sibling of [Decider V1.2](/perplexity/pplx-decider-v1.2) with the same API contract. Instead of generating text, it reads content passed...
Specifications
- Model ID
- perplexity/pplx-decider-flash-v1.2
- Canonical ID
- perplexity/pplx-decider-flash-v1.2-20261016
- Creator
- perplexity
- Added to OpenRouter
- 16.10.2026
- Context length
- 262,144
- Modality
- text+image->decisions
- Input modalities
- text, image
- Output modalities
- decisions
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Perplexity | 262,144 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.