Lightyear
Lightyear cuts the tokens coding agents send on every turn of a loop and shows the tokens and cost it saved in Fabric analytics, without changing the agent or its prompts.
Route Claude Code through Fabric (~/.claude/settings.json)
- "ANTHROPIC_BASE_URL": "https://api.anthropic.com"
+ "ANTHROPIC_BASE_URL": "https://GATEWAY_HOST/anthropic"Agent loops resend the same context on every turn: the system prompt, tool definitions, file contents and the growing conversation. Most of it has not changed since the last call, but the model is billed for all of it again. Long sessions get slower and more expensive the longer they run, and nobody can see where the tokens went.
Lightyear runs in the Fabric data plane, on the route your coding agent already uses. It reduces the tokens each request carries before it reaches the model, and records what it saved, so tokens and cost saved show up in Fabric analytics next to the rest of your usage. Because it sits in the gateway, the same routing, limits, credential brokering and traces apply to every request it touches.
Targets the context that repeats from one turn to the next.
See tokens and cost saved, by route and namespace, in Fabric analytics.
Point the agent at Fabric; Lightyear works on the route.
Qualified on Claude Code, Codex, OpenCode, Cursor, Gemini CLI, Droid and Devin.
Lightyear is token reduction for coding-agent loops. It runs in the Fabric data plane on the route your agent already uses, trims the context that repeats from one turn to the next, and records the tokens and cost it saved.
No. Point the agent at Fabric and Lightyear works on its route. For Claude Code that means setting ANTHROPIC_BASE_URL to your gateway host and sending your gateway key in a custom header; the setup guide has the exact settings.
In Fabric analytics, next to the rest of your usage: tokens and cost saved, broken down by route and namespace.
Lightyear is qualified on Claude Code, Codex, OpenCode, Cursor, Gemini CLI, Droid and Devin.
Lightyear lowers the number of tokens each request carries; adaptive model routing lowers the price per token by sending each request to the cheapest model tier that can handle it. They run on the same route and their savings add up.
Lightyear is available on both the Free and Enterprise plans.
Connect your first model, MCP server or internal API and apply consistent governance from one gateway.