All models
Liquid AI
LFM3-1.7B fastruns locally
liquid/lfm-3-1-7b
A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
Input / 1M
$0.080
USD per million tokens
Output / 1M
$0.20
USD per million tokens
Est. cost / token
$0.00000011
$0.11 per 1M, 3:1 mix
Context window
262K
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 | 1.9 GB |
| Q3_K_M | fair | 2 GB |
| Q4_K_Mrecommended | good | 2.3 GB |
| Q5_K_M | very good | 2.4 GB |
| Q6_K | excellent | 2.6 GB |
| Q8_0 | near-lossless | 3.1 GB |
| F16 | lossless | 4.7 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-07 06:00 | $0.080 | $0.20 | $0.020 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.080
- Output
- $0.20
- Cached input
- $0.020
- Blended (3:1)
- $0.11
Details
- Company
- Liquid AI
- Version
- 3.1
- Family
- Lfm
- Released
- 2026-11-06
- Parameters
- 1.7B
- Max output
- 8K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 12 min ago