LFM2.5-8B-A1B
AI model by Liquid AI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. LFM2.5-8B-A1B is a budget-tier option from Liquid AI at $0.00/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, LFM2.5-8B-A1B reports 339 tok/s output speed and 1950ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, LFM2.5-8B-A1B costs $0.00 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
LFM2.5-8B-A1BCurrent | $0.00 | $0.00 | 339 tok/s |
| GLM-4.5V (Non-reasoning) | $0.60 | $1.80 | 92 tok/s |
| Gemini 3.5 Flash (high) | $1.50 | $9.00 | 171 tok/s |
| MiMo-V2.5-Pro | $0.43 | $0.87 | 59 tok/s |
| JT-35B-Flash | — | — | — |
| Mercury 2 | $0.25 | $0.75 | 835 tok/s |