Together Link: open models in the harness you already use. Start with one command today.
Source
together.ai
Date
Why it matters
Lets teams point existing coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → harnesses at open models such as Kimi K3 and GLM 5.3 with one command and revert easily. Relevant for cutting coding-agent spend without changing workflow.
Key takeaways · AI-distilled
Together's Auto router reads only the first task of each session and picks one model for the whole session, so prompt cachingReusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.Full definition → keeps working: quick fixes go to fast, low-cost models and hard problems to frontier-capable ones.
With an Anthropic key the router chooses between Opus 5.5 and GLM 5.3; without one it chooses between GLM 5.3 and GLM 5.3 Flash, according to Together.
After each session a tracker shows what you spent next to what the same session would have cost on Opus 5.5, and billing runs on an existing Together API key with no separate contract.
Together says it serves the largest share of OpenRouter tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → for DeepSeek V4.1 Flash (40.8%), GLM 5.3 Flash (28.2%) and Kimi K3 (23.1%), as of September 30, 2026.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
prompt caching — Reusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
