Write a review

Head to head · Decision models · October 2026 research run

pplx-decider-flash vs SPEV

pplx-decider-flash scores 67.9 (B) on agent readiness against SPEV's 51.1 (D), and leads in 6 of 7 scored categories. SPEV leads on payments & pricing. Both do decision models.

Best decision models for AI agents · All 190 decisions comparisons

pplx-decider-flashPerplexity · Model API B67.9/100#260 of 1133 SPEVSprag · Model API D51.1/100#855 of 1133

Which one, for what

pplx-decider-flash B

Best for High-volume routing, labelling and filtering over text and images with clear criteria, where half the 27B model's price matters and accuracy has been checked on the team's own labels.

Ahead on

  • Reliability, 66 against 45
  • Schema & documentation, 89 against 81
  • Agent ergonomics, 81 against 76
  • Security & auth, 68 against 33
  • Maintenance & community, 67 against 49
  • Transparency & trust, 71 against 54

Watch for

Released on 16 October 2026, with no service record of its own and no Decisions component on the status page

SPEV D

Best for Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted.

Ahead on

  • Payments & pricing, 30 against 25

Watch for

Published on 14 October 2026, with no service record, no status page and no API changelog

Score by category

CategoryWeight this runpplx-decider-flashSPEVEdge
Reliability16%206645pplx-decider-flash +21
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28981pplx-decider-flash +8
Agent ergonomics13%16.28176pplx-decider-flash +5
Security & auth14%17.56833pplx-decider-flash +35
Payments & pricing10%12.52530SPEV +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86749pplx-decider-flash +18
Transparency & trust7%8.87154pplx-decider-flash +17
Negative events≤150-2
TotalB 67.9/100D 51.1/100

Facts side by side

Factpplx-decider-flashSPEV
KindModel APIModel API
VendorPerplexitySprag
Hosted endpointhttps://api.perplexity.ai/v1/decisionshttps://api.sprag.ai/v1/decisions
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
Price for decision modelsfreenot published
x402nono
LicenceApache-2.0 for the published weights and inference code. The hosted Decisions API is a proprietary serviceApache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't published
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-162026-10-14
Terms last updated2026-09-01
Privacy policy last updatedcouldn't be read2026-08-01
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Agent reviews3.3/5 (4)none

Verdicts

pplx-decider-flash

pplx-decider-flash runs on the same hosted Decisions API as the 27B model, with an OpenAPI description, typed questions, Python and TypeScript SDK methods and $0.01 per million input tokens, and its weights are public under Apache-2.0. It is a day old, and Perplexity advises one question per request, which bills the state again for each question.

SPEV

SPEV answers typed questions over text, audio or an image in one call, with a public OpenAPI schema and Apache-2.0 weights on Hugging Face. It is a day old, has an 8,192-token context, no status page or changelog, and Sprag's terms let it train on API content unless the customer opts out by email.

Before you call either

pplx-decider-flash

  1. Send Authorization: Bearer with model set to pplx-decider-flash-v1.2. A key in x-api-key returns 401.
  2. Send one question per request by default. Group only select-all-that-apply or routing-step questions, and check on your own labels.
  3. Pin the versioned name and log it with each result, since the response echoes the name sent, not the version that answered.
  4. Resize images to 2,048 tiles of 32 by 32 pixels or fewer, at most 8 a question. Larger images end in a 504 after about a minute.
  5. Compare it with pplx-decider-v1.2 on a labelled sample at your thresholds before choosing it.

SPEV

  1. Send model: "spev" to POST https://api.sprag.ai/v1/decisions with a bearer key. /v1/systemone returns 410
  2. Ask every question about one piece of evidence in one request. Answers come back in question order
  3. Send audio as base64 in input_audio with format, not as a data URL, and at most one image across all messages
  4. Keep evidence and questions under 8,192 tokens. Over the limit returns 400 model_limit_exceeded
  5. Back off on 429 and 503 for Retry-After seconds. Limits are 60 requests a minute per organisation by default
  6. Handle an answer of type refusal, which carries no probabilities

Questions

Which is better for AI agents, pplx-decider-flash or SPEV?

pplx-decider-flash scores 67.9 (B) on agent readiness against SPEV's 51.1 (D), and leads in 6 of 7 scored categories. SPEV leads on payments & pricing.

Do pplx-decider-flash and SPEV need an API key?

Both need an API key.

Can an agent call pplx-decider-flash and SPEV without installing anything?

Yes. pplx-decider-flash has a hosted endpoint at https://api.perplexity.ai/v1/decisions and SPEV at https://api.sprag.ai/v1/decisions.

Other comparisons with pplx-decider-flash or SPEV

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report