# pplx-decider (slim)

> pplx-decider is Perplexity's multimodal decision model, a fine-tune of Qwen3.8-27B. It answers yes or no, choice and score questions about text, JSON and images with probabilities, through Perplexity's hosted Decisions API or from open weights on Hugging Face.

- Full: https://www.anchorterminal.com/tools/pplx-decider.md (~7,900 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/pplx-decider.json · canonical https://www.anchorterminal.com/tools/pplx-decider
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

**B · 62.9/100 · rank #417 of 950 · #7 in Decision models · not agent-ready · confidence medium**


Assessment: The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.

## Facts

- Kind: Model API · vendor: Perplexity · category: Decision models · legal entity: not named · provenance 49/100
- Endpoint: `https://api.perplexity.ai/v1/decisions` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: Perplexity's hosted Decisions API, `POST /v1/decisions`, with `pplx-decider-v1.1-27b`. The open weights are the second route and are described, not graded as local software.
- Versions: v1.1 is current. Its weights were published on 5 October 2026. v1 was published on 1 October 2026, is marked on Hugging Face as superseded by v1.1, and still answers on the API.
- Question types: `noul` returns the probability of yes. `choice` returns a probability for each option, the top option and a confidence. `score` returns a distribution over rubric levels and the expected level.
- Request limits: 1 to 128 questions, 1 to 255 options, 1 to 10 levels, under 262,144 input tokens and a 32 MiB body. Images are base64 PNG, JPEG or WebP data URLs of at most 2,048 tiles. The API never fetches a URL.
- Rate limits: 10 requests a second per organisation on every plan. A token limit applies to large bursts, with no number given. 429 carries `Retry-After`.
- Weights: Full fine-tune of Qwen/Qwen3.8-27B with a 255-option readout in place of the generation layer. The card asks for Python 3.12 or later and a CUDA GPU with about 49 GiB for weights.
- Self-hosted server: `autojev.server` in the repository answers `POST /v1/systemone`, binds to 127.0.0.1 by default, takes up to four images and returns 529 with `Retry-After` when busy. We read the code and did not run it.
- Data handling: The API FAQ says query data is not retained and not used for training, on AWS in North America. The Privacy and Security page states zero retention for the Chat Completions API only. Terms and privacy notice were not read.
- Prices: Decision input $0.02 per 1M tokens; Decision output free per 1M tokens

- Scores: Reliability 61, Performance pending, Schema & documentation 90, Agent ergonomics 76, Security & auth 61, Payments & pricing 25, Task success pending, Maintenance & community 62, Transparency & trust 52 · total over the 7 assessed categories
- Why: Reliability, Read as a hosted model API, the surface an agent would call. · Schema & documentation, An OpenAPI 3.0.3 description of `POST /decisions` is embedded in the reference page and listed in llms.txt as `openapi-gateway-preview.json`… · Agent ergonomics, Read as an API an agent calls for a decision. · Security & auth, Read for a model API. · Payments & pricing, No x402, MPP or L402 in the guide, the reference, the pricing page or llms.txt (0). · Maintenance & community, Read for a hosted model with open weights. · Transparency & trust, The v1.1 weights are public under Apache-2.0 with a `NOTICE` naming the base model and revision, and the repository carries the training cod…
- Sources: 23, open questions: 10, both in the full twin
- Capabilities: inference.decision
- JSON: https://www.anchorterminal.com/api/v1/tools/pplx-decider.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/pplx-decider.svg` or a link to https://www.anchorterminal.com/tools/pplx-decider from a page on perplexity.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Send `Authorization: Bearer`. A key in `x-api-key` returns 401 on this endpoint.
2. Set `model` on every request. A missing or unknown model returns 400, and the guide shows a `-latest` name rejected.
3. Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.
4. Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and `error.code` changes type.
5. For the weights, use the repository's `autojev` code. The card says default causal inference does not reproduce the evaluated setup.

## Connect

```bash
curl -X POST https://api.perplexity.ai/v1/decisions \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pplx-decider-v1.1-27b","state":"The headphones sound great, but the battery stopped charging after two weeks.","questions":{"defect":{"type":"noul","instructions":"Does the review report a product defect?"}}}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Decisions API | BB | 71.5 | inference.decision | https://www.anchorterminal.com/tools/openai-decisions-api.min.md |
| Decider | B | 69.5 | inference.decision | https://www.anchorterminal.com/tools/decider.min.md |
| Laya | B | 69.2 | inference.decision | https://www.anchorterminal.com/tools/convai-laya.min.md |
| Kev | B | 67.4 | inference.decision | https://www.anchorterminal.com/tools/jaredpalmer-kev.min.md |
| Vela 2.0 | B | 66.5 | inference.decision | https://www.anchorterminal.com/tools/vela.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)