LiquidAI: LFM2.5-Embedding-350M (free) vs LiquidAI: LFM2.5-24B-A2B
LiquidAI: LFM2.5-Embedding-350M (free) is cheaper on output tokens, while LiquidAI: LFM2.5-24B-A2B offers a larger context window. Choose LiquidAI: LFM2.5-Embedding-350M (free) or LiquidAI: LFM2.5-24B-A2B based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | LiquidAI: LFM2.5-Embedding-350M (free) | LiquidAI: LFM2.5-24B-A2B |
|---|---|---|
| Provider | LiquidAI | LiquidAI |
| Input / 1M tokens | $0.00 | $0.05 |
| Output / 1M tokens | $0.00 | $0.70 |
| Context window | 512 | 128K |
| Parameters | — | — |
| Open weights | — | — |
| Released | — | — |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.