AI Agent StorePerplexity · Older API name now selects v1.2
Perplexity Decider v1 27B
This older API name now runs Decider v1.2. Use it to classify records or choose among answers you supply, but recheck any rules that rely on the model’s probabilities after the version change.
First reviewed 2026-10-02 · Checked 2026-11-03. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: pplx-decider-v1-27b. The current API accepts text and images and up to 128 named questions. Answers are probabilities, choices or ordered scores. Grouping questions can change the answers; keep the grouping consistent when testing.
Perplexity redirects pplx-decider-v1-27b and pplx-decider-v1.1-27b to pplx-decider-v1.2. The response repeats the name you sent, so it does not prove that the old model ran. Downloaded v1 weights remain a separate model.
The native limit is fewer than 256K tokens for the shared information, images and each question. Large multi-question requests can be split. Up to 128 questions, 255 choice options, 10 score levels and a 32 MiB request body. Gateway’s 262,144 declaration is separate.
Output: Yes/no probabilities, bounded choices and rubric scores. Compare decision models, limits and input costs ↗
Requests using this older name now cost $0.02 per million input tokens, with free answers and no per-request fee. Related questions can share the input charge; splitting a large request counts the shared information again. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.
Compare caching and long-context costs ↗