Sakhanda Wire
NVDA $150.96 -2.89% MSFT $508.29 +0.40% GOOGL $282.44 +0.80% META $616.38 -0.40% AMZN $267.74 +3.82%
← Back to the news

Ramp launches Router to route requests among AI models

Ramp has introduced Router, an API service that allows individuals and companies to use and switch between large language models from different providers. The service is currently available only in the United States. Ramp says it developed and used the routing system internally for the past three years.

Router supports models from OpenAI, Anthropic, DeepSeek, Moonshot, Minimax, Nvidia, xAI and Z.ai. Its routing strategies can prioritize providers’ flex usage tiers, select a model using as many as three customer-defined benchmarks, send only more difficult requests to higher-cost models, or simplify model testing without manual changes. A dashboard displays token usage, costs, latency and fallback attempts.

Router is free through the end of 2026, although customers must pay the underlying inference charges. Ramp is also offering a $26 launch credit and has not disclosed pricing for 2027. The service retains inputs, outputs and tool calls for one year by default under an opt-out policy. Ramp says it removes personally identifiable information before using retained content to improve the product. The company positions Router alongside its existing tools for monitoring AI token use and managing related spending.

Written by Sakhanda Wire AI from reporting by TechCrunch. Facts, quotes and full context are in the original article below.

Originally published by TechCrunch on

Read the original on TechCrunch ↗

The reporting and the image belong to TechCrunch and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news