Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.
Added Aug 12, 2026
Model weightsContext Window
128.0K
Max Output
32.8K
Input Price (Auto)
$0.10/1M
Output Price (Auto)
$0.20/1M
Cache Read (Auto)
$0.050/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
No benchmark data is available yet for this model.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare LFM2.5 2.6B with similar models from the same provider or model family.
Ornith 1.5 397B
ornith-ai/ornith-1.5-397bOrnith 1.5 397B is an open-weight mixture-of-experts model built for agentic coding, tool use, image understanding, and long-context workflows. This variant disables thinking for faster direct responses.
Ornith 1.5 397B Thinking
ornith-ai/ornith-1.5-397b:thinkingOrnith 1.5 397B with thinking enabled for deeper agentic coding, reasoning, tool use, image understanding, and long-context workflows.
Ornith 1.5 9B Thinking
ornith-ai/ornith-1.5-9b:thinkingOrnith 1.5 9B with thinking enabled for more deliberate agentic coding, tool use, visual understanding, and long-context work.
Ornith 1.5 9B
ornith-ai/ornith-1.5-9bOrnith 1.5 9B is an FP8 dense open-weight model built for agentic coding, tool use, visual understanding, and efficient long-context work. This variant disables thinking for faster direct responses.
Ornith 1.5 35B
ornith-ai/ornith-1.5-35b-a3bOrnith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.
Ornith 1.5 35B Thinking
ornith-ai/ornith-1.5-35b-a3b:thinkingOrnith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.