Perplexity's Decider V1.2 models now available on AI Gateway

Perplexity's Decider V1.2 27B and Decider Flash V1.2 4B decision models are now available on Vercel's AI Gateway, the company announced. Both are multimodal decision models that answer typed questions with probabilities — Boolean questions return the likelihood of yes, Choice questions select from user-defined categories, and Score questions assess content against an ordered rubric — for tasks such as classifying content, routing requests, and scoring text, structured records, and images. The 27B model is positioned for nuanced judgments and detailed rubrics, while the 4B Flash model targets high-volume labeling, filtering, and routing with clear criteria; inference uses provider pricing with no markup or platform fee, including under BYOK.

Perplexity Decider V1.2 27B https://vercel.com/ai-gateway/models/pplx-decider-v1.2 and Decider Flash V1.2 4B https://vercel.com/ai-gateway/models/pplx-decider-flash-v1.2 are now available on AI Gateway https://vercel.com/ai-gateway . Both are multimodal decision models https://vercel.com/docs/ai-gateway/modalities/decision for classifying content, routing requests, and scoring text, structured records, and images. The models answer typed questions with probabilities. Boolean questions return the likelihood of yes, Choice questions select from categories you define, and Score questions assess content against an ordered rubric. Your application can use those results to route a support ticket, flag a damaged product, or send an uncertain decision for human review. Multiple questions can share the same input in one request. Decider V1.2 27B perplexity/pplx-decider-v1.2 is the larger model, for nuanced judgments and detailed rubrics. Decider Flash V1.2 4B perplexity/pplx-decider-flash-v1.2 is the smaller model, for high-volume labeling, filtering, and routing with clear criteria. The examples below use perplexity/pplx-decider-v1.2 and check the same delivery report through the AI SDK https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk , the Decisions API https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-decisions , and the TypeSafe-compatible API https://vercel.com/docs/ai-gateway/sdks-and-apis/typesafe : For image input, embed base64 image url objects in JSON state through the AI SDK or TypeSafe-compatible API. See Perplexity's image format https://docs.perplexity.ai/docs/decisions/quickstart images-in-state and the decision models documentation https://vercel.com/docs/ai-gateway/modalities/decision for request formats and question types. Explore Decider V1.2 27B in the model playground https://vercel.com/ai-gateway/models/pplx-decider-v1.2 , or try Decider Flash V1.2 4B https://vercel.com/ai-gateway/models/pplx-decider-flash-v1.2 . Use AI Gateway to call models with one API key and monitor usage and cost in one place. Decision requests are recorded in request logs https://vercel.com/docs/ai-gateway/observability-and-spend/logs and included in spend budgets https://vercel.com/docs/ai-gateway/observability-and-spend/budgets . Inference uses provider pricing without a markup or platform fee. This also applies when you supply your own provider credentials through BYOK https://vercel.com/docs/ai-gateway/authentication-and-byok/byok . Browse the decision model catalog https://vercel.com/ai-gateway/models?modality=decision to see the available options.