Compare models
Showing the latest models, add more to compare
inclusionai/ling-3.1-flash Details | perplexity/pplx-decider-v1-27b Details | stealth/fledge-alpha Details | |
|---|---|---|---|
| Overview | |||
| Description | Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. Available through BYOK keys (Novita and OpenRouter list it at $0). | 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). | Fledge Alpha is a free-tier stealth preview reasoning model with text and image input and tool use. It always reasons with adjustable effort (low, high, or max) over a 1M-token context window. No lab, specifications, or benchmarks are published for it yet. |
| Category | Text Generation | Text Generation | Text Generation |
| Context length | 262K | 262K | 1M |
| Providers | 2 | 1 | 2 |
| Pricing (per 1M tokens) | |||
| Input | $0 | $0.04 | $0 |
| Output | $0 | $0 | $0 |
| Capabilities | |||
| Reasoning | – | – | |
| Tool calling | – | ||
| Vision | – | ||
| Streaming | – | ||
| Token activity (30 days) | |||
| Usage |