Compare models
Showing the latest models, add more to compare
perplexity/pplx-decider-v1-27b Details | strandsagents/strands-decider-2b Details | unbiased/pareto-26.10-preview Details | |
|---|---|---|---|
| Overview | |||
| Description | PPLX Decider v1 (27B) is Perplexity's multimodal decision model: send application state and typed questions (noul / choice / score) and get back a probability distribution over a fixed set of answers — it returns probabilities, not generated chat text, and produces no free-form output. `state` may be a string, an object, or an array of OpenAI-style `image_url` parts carrying base64 PNG/JPEG/WebP data URLs, so it also scores images. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). | Strands Decider 2B is AWS Strands Labs' small open-weight decision model: send application state and typed questions (noul / choice / score) and get calibrated probabilities back in one forward pass — it returns answers with confidence scores, not generated chat text, and produces no free-form output. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). | Pareto 26.10 Preview is Unbiased's newer composite model — it blends several language models into one answer, takes text and image input, and returns text over a 1,048,576-token context window (131,072 max completion). It is aimed at research, coding, and agentic workflows and is priced well under the current unbiased/pareto ($0.80 vs $2.50 per 1M input, $3.20 vs $7.50 per 1M output). A distinct, official OpenRouter listing — not a repack of the older unbiased/pareto row, which stays a disabled Cloudflare tombstone (#3368). |
| Category | Text Generation | Text Generation | Text Generation |
| Context length | 262K | 4K | 1M |
| Providers | 1 | 1 | 1 |
| Pricing (per 1M tokens) | |||
| Input | $0.04 | $0 | $0.80 |
| Output | $0 | $0 | $3.20 |
| Capabilities | |||
| Reasoning | – | – | – |
| Tool calling | – | – | |
| Vision | – | ||
| Streaming | – | – | |
| Token activity (30 days) | |||
| Usage |