LFM2.5-24B-A2B

LFM2.5-2.6B

liquid

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 knowledge-heavy tasks. Prompts and outputs may be retained and used to train Liquid models.

Context

128K

Max output

8.2K

Released

2026-08-11

Input

$0.35/M

Output

$0.5/M

Cache read

$0.04/M

d1.1

liquid

d1.1 is Liquid AI's structured decision model, served as a System One endpoint and the successor to d1. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, and policy checks that need a fast, scored answer instead of prose.

Context

66K

Max output

59.0K

Released

2026-10-27

Input

$0.02/M

Output

$0/M

Cache read

$0.02/M

d1-ultra

liquid

d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text. It uses the same /v1/systemone schema as other OpenRouter Decisions models, so it suits routing, classification, moderation, and visual checks that need a fast, scored answer instead of prose.

Context

33K

Max output

29.5K

Released

2026-10-15

Input

$0.042/M

Output

$0/M

Cache read

$0.042/M