Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | CohereLabstiny-aya-fireRemove × | liquidLiquidAI: LFM2.5-24B-A2BRemove × |
|---|---|---|
| What’s different | Open weights | 24B total, 2.45B active parameters; always reasons before answering, with GGUF and MLX releases for local deployment. |
| Date | Feb 13, 2026Listed | Oct 13, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $0.05 in / $0.70 out/ 1M tokensLiquid · via OpenRouter · all routes ↗liquid/fp8 · quantization=fp8 |
| Provider endpoints | 1 endpoint → | 2 endpoints → |
Specifications | ||
| Context window | — | 128K |
| Max output | — | 8.2K |
| Parameters | — | 24B |
| Tool calling | Not reported | Supported |
| Structured output | Not reported | Supported |
| Reasoning | Not reported | Supported |
| Prompt caching | Not reported | Supported |
| Open weights | Supported | Supported |