TL;DRPerplexity Decider v1 27B by Perplexity costs $0.02 per 1M input tokens and $0.00 per 1M output tokens and carries a context window of 262K tokens — observed 2026-10-23.
Canonical idpplx-decider-v1-27b
Context window262K tokens Access typeOpen Weight
Blended $/1M$0.01575% input / 25% output
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Capability evidence
Multimodal & GroundedUnavailable Instruction FollowingUnavailable Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
Runtime measurements| Measurement | Value | Observed | Last good | Evidence |
|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable | |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
Price components| Component | USD | Evidence |
|---|
| Input / 1M tokens | $0.02 | |
| Output / 1M tokens | $0.00 | |
| Cache read / 1M tokens | Unavailable | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $0.015 | |
| Cost per successful task (LiveBench) | Unavailable | |
Self-hosted listingPerplexity lists $0.02 per million input tokens for pplx-decider-v1-27b, free output tokens, and no per-request fee. State, questions, and images all count toward input usage. This is a typed-decision endpoint, so compare cost per completed decision as well as the token rate. Open weights are separately available under Apache 2.0; these prices are for the hosted Perplexity API, not local GPU costs. Since October 16, 2026, requests that name pplx-decider-v1-27b run pplx-decider-v1.2 and bill at $0.02.The rates above are a hosted price matched from another provider, not a first-party list price.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Modelled monthly cost$0.0422
Modelled tokens2.82M
Benchmark record
12 matched benchmark rows with their published value, unit, and provenance.
external
external benchmarks| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|
| WinoGrande (Perplexity panel) WinoGrande (Perplexity panel) | 83.30 | Ambiguous-reference resolution | Depends on the sampled tasks and label mapping | Perplexity Decider v1 27B model card |
| FinancialPhraseBank (Perplexity panel) FinancialPhraseBank (Perplexity panel) | 84.18 | Financial sentiment classification | Depends on the sampled tasks and label mapping | Perplexity Decider v1 27B model card |
| RAGTruth (Perplexity panel) RAGTruth (Perplexity panel) | 88.80 | Unsupported-claim detection |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-10-23 13:17 UTC.
ModelScale