Jev vs pplx-decider: TypeSafe's decision model against Perplexity's

The short answer

pplx-decider is a decision model from Perplexity. Like Jev, it reads one state and answers typed Noul, Choice and Score questions with probabilities. It differs in four ways. It reads images, it accepts 262,144 input tokens per request, it allows 255 options on a Choice and 128 questions per call, and its weights are open under Apache 2.0. It is also a little cheaper, at $0.04 per million input tokens against $0.042 for Jev.

It is not a drop-in swap. It has its own endpoint and request format, so code written for Jev needs changes and TypeSafe’s SDKs do not work with it. Jev has the longer record, the SDKs and a wire format that several other vendors accept. The best outside comparison so far is the Decision Index, where Jev scores 57.91 and pplx-decider 56.40.

Jev vs pplx-decider at a glance

Sources: TypeSafe’s models page and SDK docs, Perplexity’s quickstart and the model card, checked 2 October 2026. Perplexity says it plans to lower its price, so check its docs for the current rate.

What each model does

Both models take a state and a set of named questions and return a probability for each answer. Neither writes text. Choice, Score and Noul covers the three question types, and pplx-decider uses the same three. In pplx-decider a Noul returns the probability of yes, a Choice returns one probability per option, and a Score returns a probability-weighted average level.

The request differs. Perplexity’s body has model, state and questions, as Jev’s does, but it goes to https://api.perplexity.ai/v1/decisions, the answers come back under an answers object, and the key goes in an Authorization: Bearer header. Images go in the state array as base64 PNG, JPEG or WebP data URLs, up to 2,048 tiles of 32 by 32 pixels each. The API never fetches image URLs.

Jev’s /v1/systemone format is also used by Solar Decide, d1, Decider 1 and several open projects, and Clef takes the same fields, as Jev alternatives lists. pplx-decider is not on that list. Moving code means changing the endpoint, the response parsing and the model name, and dropping the TypeSafe client.

What the benchmarks show

Perplexity did not publish a head-to-head test against Jev under shared conditions. Three sources give numbers, and they are not directly comparable with each other.

Perplexity’s model card. The card reports 85.71% across 11 benchmarks for pplx-decider against 74.76% for the base Qwen3.8-27B, and says it measured pplx-decider through its own API. Its table also has a Jev column, at 84.51% overall, and does not say how those Jev figures were obtained. Jev is higher on six of the 11 rows, among them WinoGrande (90.70% against 83.30%) and BBH (94.27% against 82.80%). pplx-decider is higher on the other five, among them RAGTruth (88.80% against 77.27%) and Circa (89.20% against 84.60%). This is a vendor-run table.

The Decision Index. The Decision Index 0.2.1 is a third-party board with one suite and one set of rules for every entry. As of 2 October 2026 its data lists pplx-decider-v1-27b, linked to Perplexity’s weights, with a headline score of 56.40 against 57.91 for Jev 1.13. That puts it fourth of the 71 rows on the board. The board’s calibration error, the average gap between stated confidence and how often the model is right, is 0.018 for pplx-decider and 0.074 for Jev, and lower is better. The Index is one person’s suite, and its note says the board’s Jev latency is a hosted-API round trip that is not comparable with the on-card figures of the open models.

The same task, two setups. RAGTruth is on the card and on the Index, and the two give different numbers for the same model. The card has pplx-decider at 88.80% and Jev at 77.27%. The Index has them at 80.34 and 76.53. The setups, metrics and who ran them differ, so do not read one gap against the other.

Perplexity itself publishes no calibration figures. The 0.018 above comes from the Index. Neither vendor’s numbers have been reproduced on your data, so run both on a sample of it.

Speed, cost and hosting

Perplexity gives times by input size, from its own tests on 30 September 2026: under 2 seconds for a few hundred input tokens, about 5 seconds at roughly 90,000, about 14 at roughly 190,000 and about 23 just under the limit. It publishes no median or percentile. TypeSafe’s own figure for Jev is 70ms to 500ms end to end, also unverified by a third party. The two sets of numbers use different measures, so they cannot be set against each other. Time both from your own region with your own state sizes.

Price is close: $0.04 against $0.042 per million input tokens, with output free on both. That is $0.002 a million less, and Perplexity’s CEO said on 1 October 2026 that it intends to cut the price further. Jev’s rate limit is higher, at 40 requests per second against Perplexity’s 10 per organization.

Because the pplx-decider weights are Apache 2.0, you can run the model yourself. The model card says that takes Python 3.12 or newer and a CUDA GPU with room for about 49 GiB of weights plus working memory. Jev has no downloadable weights.

When to use which

• You send very long states. pplx-decider takes 262,144 input tokens. Jev’s state limit is 32,000.
• You classify images. pplx-decider reads them. Jev reads text only.
• You ask many questions about one state. pplx-decider allows 128 per call. Jev does not document a limit, so check it before you rely on a large batch.
• You want weights you control. Only pplx-decider offers them, under Apache 2.0.
• You want the lowest price. pplx-decider is slightly cheaper today, and Perplexity plans a further cut. The gap is small.
• You need independent results. Both are on the Decision Index, where Jev scores higher. Jev also has the longer public record.
• You already use TypeSafe’s SDKs or the /v1/systemone format. Stay on Jev. Several other vendors accept that format, so you keep a way out.
• You need a higher request rate. Jev’s limit is 40 requests per second. Perplexity’s is 10 per organization.

See Jev alternatives for the other options.

FAQ

Is pplx-decider a Jev alternative?

Yes, for the job. Both answer typed Noul, Choice and Score questions with probabilities about one state. It is not a drop-in swap, because it uses Perplexity’s /v1/decisions endpoint and its own response shape. Moving means changing the endpoint, the model name and the parsing, and rerunning your own evals.

Is pplx-decider better than Jev?

Not on the one outside test. The Decision Index scores Jev 57.91 and pplx-decider 56.40, but pplx-decider has much lower calibration error. Perplexity’s own card shows each ahead on some benchmarks, which it ran itself. It has advantages in context size, images and open weights. Test both on your own data.

Does pplx-decider read images?

Yes. You put base64 PNG, JPEG or WebP data URLs in the state array, up to 2,048 tiles of 32 by 32 pixels each, and the API never fetches an image URL. Jev reads text only. Perplexity publishes no image benchmark, so test it on your own images before relying on it.

Is pplx-decider free or open source?

The weights are free under Apache 2.0 on Hugging Face and are not gated. Perplexity’s hosted Decisions API is not free. It costs $0.04 per million input tokens as of 2 October 2026, with output free. Running the weights yourself needs a CUDA GPU with about 49 GiB for the weights plus working memory.

Can I use TypeSafe’s SDKs with pplx-decider?

No. TypeSafe’s Python and TypeScript SDKs call /v1/systemone, and pplx-decider answers at /v1/decisions with a different response shape. Perplexity’s own SDKs document no decisions method, so its quickstart calls the endpoint with httpx or fetch. Changing the base URL alone will not work.

Examples

Decision Index: Jev against 50+ open decision models

A leaderboard that runs Jev and 54 open System One models and clones through the same 120,000-question suite on one RTX PRO 6000, scoring accuracy and calibration. Jev leads the 0.2 edition at 51.67 on a chance-corrected scale, with AutoJev-27B close behind at 50.94.

apolinario (poli) (@multimodalart)43k viewsOpenDecision Index: Jev against 50+ open decision models on huggingface.co

Article