Liquid
LFM2.5-2.6B
Released 2026-08-11
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...
You send / 1M
$0.350
tokens in
It replies / 1M
$0.500
tokens out
Memory
128K
tokens it can read at once
Typical request
Free
1,000 words in, 400 out
Data privacy
No training or retention: Unknown. Check the provider's terms before sending sensitive data.
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 8K tokens
- Repeated text is billed at $0.040 per 1M (prompt caching)
- Intelligence score: 8.4 / 100 (Artificial Analysis)
Similar models
- Qwen3 30B A3BQwen · $0.120 in / $0.500 out per 1M
- Hy3Tencent · $0.132 in / $0.528 out per 1M
- Nemotron 3 SuperNVIDIA · $0.080 in / $0.450 out per 1M
- Hunyuan A13B InstructTencent · $0.140 in / $0.570 out per 1M
- DeepSeek V3.2DeepSeek · $0.280 in / $0.420 out per 1M
- Solar Pro 4Upstage · $0.150 in / $0.600 out per 1M