Perplexity / perplexity/pplx-decider-v1.1-27b
PPLX Decider v1.1 27B - access through LLMTR
PPLX Decider v1.1 27B is the current version of Perplexity's decision model. It evaluates a state you send (text, JSON or images) against typed questions and returns one structured answer per question: the probability of a yes/no statement, a pick from up to 255 options you define, or a position on your own scale of up to 10 levels; choices and scores also carry a confidence value. It does not generate text. Images go in an array state as base64 PNG, JPEG or WebP data URLs. Each question, together with the state, must stay under 262,144 tokens. The Structured Decisions documentation covers the request format, question types and billing.
Technical specifications
| Canonical ID | perplexity/pplx-decider-v1.1-27b |
|---|---|
| Provider | Perplexity |
| Context window | 262,144 tokens |
| Operations | SYSTEM_ONE |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| SYSTEM_ONE | INPUT_TEXT | PER_1M_TOKENS | $0.020000 |
| SYSTEM_ONE | OUTPUT_TEXT | PER_1M_TOKENS | Not available |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"perplexity/pplx-decider-v1.1-27b","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Perplexity Decider API: probability-based decisions on /v1/systemone at $0.02 per 1M tokens - perplexity/pplx-decider-v1.1-27b is a decision model that answers typed questions about a state you send with probabilities, and generates no text. On LLMTR it is called at https://llmtr.com/v1/systemone for $0.02 per 1M input tokens; output has no price. The state is counted again for each question.
- Verifying agent output: probabilities from Perplexity Decider instead of a text-writing judge - The agent's answer is sent to perplexity/pplx-decider-v1.1-27b as the state, together with the user's question and the tool result; the checklist becomes noul questions, and each returns a probability of yes between 0 and 1. An answer below the threshold goes to a person. Input costs $0.02 per 1M tokens.
- Image classification API: yes/no, category and quality score with Perplexity Decider - perplexity/pplx-decider-v1.1-27b evaluates a base64 image added to the state array against your questions and returns a yes/no probability, a category or a quality score. On LLMTR it is called at https://llmtr.com/v1/systemone; the image is counted again for each question, at most about 2,050 tokens per question.
Related models
- Sonar perplexity/sonar
- Sonar Pro perplexity/sonar-pro
- Sonar Reasoning Pro perplexity/sonar-reasoning-pro
- Sonar Deep Research perplexity/sonar-deep-research
- PPLX Embed v1 0.6B perplexity/pplx-embed-v1-0.6b
- PPLX Embed v1 4B perplexity/pplx-embed-v1-4b
- PPLX Embed Context v1 0.6B perplexity/pplx-embed-context-v1-0.6b
- PPLX Embed Context v1 4B perplexity/pplx-embed-context-v1-4b