Liquid AI's LFM2.5-24B-A2B now available on AI Gateway
LFM2.5-24B-A2B from Liquid AI is now available on AI Gateway.
LFM2.5-24B-A2B is an open-weight Mixture-of-Experts reasoning model with 24B total parameters and 2B active per token for efficient inference. It is especially strong at tool calling, automation, and instruction following. Combined with its small active parameter count, that makes the model well suited to fast, low-cost agents.
The model has a 128K-token context window, with room for documents, tool results, and extended task histories. You can access it with one API key, without creating a separate provider account.
Use liquid/lfm2.5-24b-a2b as the model name:
To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:
Then select liquid/lfm2.5-24b-a2b in the agent. See the coding agents guide for details.
Try LFM2.5-24B-A2B in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all language models available on AI Gateway.