All models
Liquid AI
LFM2.5-2.6B fastruns locally
liquid/lfm-2-5-2-6b
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Input / 1M
$0.35
USD per million tokens
Output / 1M
$0.50
USD per million tokens
Est. cost / token
$0.000000387
$0.39 per 1M, 3:1 mix
Context window
128K
max output 8K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 2.5 GB |
| Q3_K_M | fair | 2.7 GB |
| Q4_K_Mrecommended | good | 3 GB |
| Q5_K_M | very good | 3.3 GB |
| Q6_K | excellent | 3.6 GB |
| Q8_0 | near-lossless | 4.3 GB |
| F16 | lossless | 7 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.35 | $0.50 | $0.040 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.35
- Output
- $0.50
- Cached input
- $0.040
- Blended (3:1)
- $0.39
Details
- Company
- Liquid AI
- Version
- 2.5
- Family
- Lfm
- Released
- 2026-08-11
- Parameters
- 2.7B
- Max output
- 8K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 32 min ago