Models / liquid
LFM2.5-2.6B
by liquid ·
liquid/lfm-2.5-2.6bLFM2.5-2.6B 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...
reasoningtool-usereleased 2026-08-11
Legal score · raw
-
not yet benchmarked
Context
128K
max output 8K
Input
$0.44
per 1M tokens
Output
$0.63
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.05
8.8x cheaper than uncached
Uncached input
$0.44
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.