pplx-decider-flash-v1.3
- Family
- PPLX Decider
- Released
- 2026-11-12
- Context
- 256K
- Parameters
- 4B
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Developing AI for complex problem-solving.
Cheapest of 2 routes · Perplexity Labs
Developing AI for complex problem-solving.
Cheapest of 2 routes · Perplexity Labs
About
pplx-decider-flash-v1.3 is Perplexity's 4B multimodal decision model, released November 12, 2026 with open weights under Apache 2.0. It is fine-tuned from Qwen3.5-4B and distilled from the 27B pplx-decider-v1.3, sharing its request schema and capabilities, including text and image input and the new locate span-extraction questions. Like the other PPLX Decider models it returns probabilities for yes/no, choice and score questions instead of text. It is served through the Perplexity Decisions API (alias pplx-decider-flash-latest now selects it) at $0.01 per 1M input tokens with free output, and is listed on OpenRouter and Vercel AI Gateway.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Perplexity Labs | $0.010 | Free | Serverless |
| Vercel AI Gateway | $0.010 | Free | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
pplx-decider-flash-v1.3perplexity-ai/pplx-decider-flash-v1.3perplexity/pplx-decider-flash-v1.3pplx-decider-flash-latest