All models
Liquid AI
LFM2.5-24B-A2B fastruns locally
liquid/lfm-2-5-24b-a2b
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
Input / 1M
$0.050
USD per million tokens
Output / 1M
$0.70
USD per million tokens
Est. cost / token
$0.000000213
$0.21 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 | 12.9 GB |
| Q3_K_M | fair | 14.6 GB |
| Q4_K_Mrecommended | good | 17.7 GB |
| Q5_K_M | very good | 20.2 GB |
| Q6_K | excellent | 23 GB |
| Q8_0 | near-lossless | 29.1 GB |
| F16 | lossless | 52.7 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.050 | $0.70 | $0.025 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.050
- Output
- $0.70
- Cached input
- $0.025
- Blended (3:1)
- $0.21
Details
- Company
- Liquid AI
- Version
- 2.5
- Family
- Lfm
- Released
- 2026-10-13
- Parameters
- 24B (2B active)
- Max output
- 8K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 32 min ago