Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | zai-orgGLM-5.3-Flash-BF16Remove × | perplexityPerplexity: Decider V1.2Remove × | respanRespan: Span-02Remove × |
|---|---|---|---|
| What’s different | Image input · Open weights | Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding Decider V1.1 27B with the same API contract. Instead of generating text, it reads content passed as state... | Set a thinking deadline in milliseconds; returns typed decisions or direct numbers with confidence, and accepts up to four images. |
| Date | Aug 25, 2026Listed | Oct 16, 2026Listed | Oct 16, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | $0.02 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.01 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 1 endpoint → | 1 endpoint → |
Specifications | |||
| Context window | — | 262.1K | 131.1K |
| Max output | — | 235.9K | 118K |
| Parameters | — | — | — |
| Tool calling | Supported | Not reported | Not reported |
| Structured output | Supported | Not reported | Not reported |
| Image input | Supported | Supported | Supported |
| Open weights | Supported | Not reported | Not reported |