Tracer
Combining open-source AI models for better answers at lower cost
About Tracer
Tracer is an AI research lab building more capable and efficient AI through model coordination. We research adaptive inference, ensembling, and systems in which multiple open-source models work together to produce capabilities beyond any single model. Our work spans reasoning, code, research, and agentic systems, with the goal of making advanced intelligence more accessible and economical.
Public traction evidence
Each signal links to the public source used for attribution.
- X
Today we’re launching Echo: Fable-level quality at ~1/3 the inference cost using open-weight models.
Today we’re launching Echo: Fable-level quality at ~1/3 the inference cost using open-weight models. Echo matches or nearly matches Fable on math, science, and the coding benchmarks we currently cover, while trailing on multilingual and broader knowledge. 🧵
- X
Today, we’re introducing Echo: one adaptive model built entirely from a pool of open-weight models.
Today, we’re introducing Echo: one adaptive model built entirely from a pool of open-weight models. On our first internal task mix, Echo reached Fable-level results at roughly 1/3 of the total inference cost. Try it: https://t.co/oIymERQqB2 https://t.co/R8XJg4SCLh
- X
Tracer 0.2.0 is out New: tracer scan reads your LLM classification traces and tells you, on held-out data it never saw, how much traffic a near-free model can already take over, with an interactive 3D map of your embedding space and more...
Tracer 0.2.0 is out New: tracer scan reads your LLM classification traces and tells you, on held-out data it never saw, how much traffic a near-free model can already take over, with an interactive 3D map of your embedding space and more... 👇🧵 https://t.co/FoJhYZH3ud
- X
Tracer just launched on @ycombinator's Launch YC! Tracer: Fable-level AI at 1/3 the cost using open-weight models.
Tracer just launched on @ycombinator's Launch YC! Tracer: Fable-level AI at 1/3 the cost using open-weight models. Check them out: https://t.co/QI1TjFwwSF
- X
a lot of things are coming in the coming weeks, stay tuned!
a lot of things are coming in the coming weeks, stay tuned!
- X
Echo is now natively supported in OpenCode 🎉 echo/echo is officially in https://t.co/7Izd2WIoOu 🫡 Try now at https://t.co/SrumQkNrN7
Echo is now natively supported in OpenCode 🎉 echo/echo is officially in https://t.co/7Izd2WIoOu 🫡 Try now at https://t.co/SrumQkNrN7
- X
Echo gets Fable-level results at ~1/3 the cost and can be customized to your workload.
DeepSeek raised prices. We’ll pay you to switch. Echo gets Fable-level results at ~1/3 the cost and can be customized to your workload. Works in OpenCode, Cline & Zed. Top up $20 → we add another $20. Only for the next 1,000 users. Go burn it.
- X
Google’s selected bid for Spirit Airlines’ data + software was $10M.
Google’s selected bid for Spirit Airlines’ data + software was $10M. Under the assumptions in our new paper, that price only requires ~0.236% persistent economic uplift over 3 years to break even. We tried to work out what that actually means for pricing proprietary data in AI.