← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
LFM2.5-2.6B Pricing
LiquidAI · liquid-lfm-2-5-2-6b
Input / 1M tokens
$0.350
Output / 1M tokens
$0.500
Context window
128k tokens
≈ 171 pages of text
Max output
8,192 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0006
1,000 requests / month$0.62/mo10,000 requests / month$6.20/mo100,000 requests / month$62.00/moEstimate your own workloadOpens the calculator with LFM2.5-2.6B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Low-latency inference and high throughput on modest hardware due to small parameter count and open weights. Suitable for high-volume simple classification or extraction tasks.
The business tradeoff
Weak performance on multi-step reasoning or nuanced generation relative to larger models. Limited ecosystem support and fewer production deployment patterns than established open-weight families.
Cheaper from LiquidAI
Head-to-head
Vendor list rates, as of Oct 24, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.