Ramp launches Router LLM gateway to cut inference costs by 40%
round · x · 2026-08-22
Ramp has officially launched Router, an LLM gateway designed to reduce inference costs by intelligently routing requests to the most cost-effective model that meets performance needs. The company claims an average reduction of 40% in AI costs.
Key Features:
- Unified Access: Access all models through a single API key and bill.
- Smart Routing: Automatically switches models to save costs with an enabled auto mode.
- Cost Optimization: A case study highlights a customer reducing model costs by 92% while running billions of tokens through Router.
- Compatibility: Supports both closed and open-source models, US-hosted with Zero Data Retention (ZDR) options.
The product targets both CTOs for optimal model selection and CFOs for lower spending.
More from Infra
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- vLLM ships Day-0 LoRA RL for Muse Spark Open, lifting AIME from 0.56 to 0.85 — vllm_project · 2026-10-16
- DSpark draft model for Muse Spark Open proposes 7 tokens per pass with 23-42% acceptance — vllm_project · 2026-10-16
- Cloudflare Stream's WebRTC ultra-low-latency live streaming is now Generally Available — ritakozlov · 2026-10-16
- YC-backed Overshoot launches inference optimization, claims $5M saved for AI teams — ycombinator · 2026-10-16