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...
With CoreAI, you can start chatting with LiquidAI: LFM2.5-2.6B instantly — no separate subscription needed. CoreAI lets you chat with LiquidAI: LFM2.5-2.6B alongside 300+ other AI models from Liquid and other providers like OpenAI, Anthropic, Google, Meta, and more.
Among the 450 chat models on CoreAI, LiquidAI: LFM2.5-2.6B ranks #382 by context window — 128K tokens, roughly 96,000 words or 192 pages of text in a single conversation. On price, it is the #141 cheapest of 152 budget-tier models by input cost. It joined the catalog on 2026-08-11. It supports step-by-step reasoning (thinking mode).
Every model in this table is available on CoreAI — open the web app and run the same prompt through LiquidAI: LFM2.5-2.6B and LiquidAI: LFM2.5-24B-A2B side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00060 on LiquidAI: LFM2.5-2.6B's raw per-token rates; a heavy session with a 50K-token document costs about $0.020. On CoreAI you don't juggle these numbers — one subscription covers LiquidAI: LFM2.5-2.6B and 300+ other models under a plan usage limit, with no API keys. See plans.
LiquidAI: LFM2.5-2.6B handles 128K tokens of context — roughly 96,000 words, or about 192 pages of text in one conversation.
LiquidAI: LFM2.5-2.6B's underlying rates are $0.35 per 1M input tokens and $0.5 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — LiquidAI: LFM2.5-2.6B is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.
Yes. LiquidAI: LFM2.5-2.6B can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.
Open the CoreAI web app or the iOS/Android app, pick LiquidAI: LFM2.5-2.6B in the model selector, and chat — no API key, no per-token billing. One subscription covers LiquidAI: LFM2.5-2.6B and 300+ other models.
The closest alternatives on CoreAI are LiquidAI: LFM2.5-24B-A2B, NVIDIA: Nemotron 3.5 Content Safety (free), IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with LiquidAI: LFM2.5-2.6B and 300+ other AI models — all in one app.