LFM 2.5 24B A2B
Toolsliquid/lfm-2.5-24b-a2b128K context · Oct 2026 · 2 upstreamsupstream上游
Liquid AI LFM2.5-24B-A2B is an open-weight reasoning mixture-of-experts model with 24B total and about 2B active parameters per token. It always reasons before it answers and is built for fast agents, tool use and structured output, with a 128K context window.
Bring your own keyAnyRouter has no platform route for LFM 2.5 24B A2B. Requests use your key and bill your provider account. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 128K
- inputđầu vào输入 / 1M (list)
- $0.05
- outputđầu ra输出 / 1M (list)
- $0.70
- routestuyến路由
- 2
- speed, 24htốc độ, 24h速度,24h
- —
Upstreams
2- 1OpenRouterYour key · not addedyour planTPS —TTFT ——
- 2Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
- Up
- No traffic
- Down
Try itDùng thử试用
Send a promptGửi một prompt发送提示词
Details
- Owner
- Liquid
- Kind
- Chat
- Released
- Oct 2026
- Context
- 128K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
Quick start
curl https://anyrouter.dev/api/v1/chat/completions \ -H "Authorization: Bearer $ANYROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "liquid/lfm-2.5-24b-a2b", "messages": [ { "role": "user", "content": "Say hi in 3 words." } ] }'
- Fast agents and tool calling
- Low-cost reasoning for high-volume workloads
Architecture and licenseKiến trúc và giấy phép架构与许可
StrengthsĐiểm mạnh优势[1],[2]
- Competitive with a larger MoE on agentic and tool-use benchmarks
- Reasoning at 2B active parameters keeps each thinking token cheap
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- liquid.ai
- Model cardThẻ mô hình模型卡
- huggingface.co
SourcesNguồn来源
- [1]LFM2.5-24B-A2B model cardaccessedtruy cập访问于 2026-10-17
- [2]LFM2.5-24B-A2B: Built for Fast On-Device Agentsaccessedtruy cập访问于 2026-10-17
Upstreams and pricingUpstream và giá上游与价格
Share cards3 images



AliasesBí danh别名 (1)
liquid/lfm2.5-24b-a2b
params: max_tokens · temperature · top_p · stop · tools · tool_choice · reasoning · response_format
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.