RentGPU RentGPU
GPU finden →
by Liquid

LiquidAI: LFM2.5-24B-A2B.

text closed 128K ctx
Cheapest input
$0.05/M
on OpenRouter
Cheapest output
$0.7/M
on OpenRouter
Hosted equiv.
~$0.25/hr
@ 100 tok/s on OpenRouter

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

Hosted API only

No self-host path — closed weights.

LiquidAI: LFM2.5-24B-A2B's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.05 $0.7 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run LiquidAI: LFM2.5-24B-A2B?
LiquidAI: LFM2.5-24B-A2B is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access LiquidAI: LFM2.5-24B-A2B?
LiquidAI: LFM2.5-24B-A2B is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run LiquidAI: LFM2.5-24B-A2B?
API pricing starts at $0.05/M input tokens and $0.7/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is LiquidAI: LFM2.5-24B-A2B open-source or proprietary?
LiquidAI: LFM2.5-24B-A2B is a proprietary model from Liquid. Access is API-only — there are no public weights to download.