Loading post…
Together AIAnnouncement
Together Link: open models in the harness you already use. Start with one command today.
Summary
Together Link connects coding agents to over 40 production-tier open models on Together AI, cutting model spend by over 50% compared to premium closed models. It integrates with Claude Code, Claude Desktop, Codex, OpenCode, and Pi without requiring any workflow changes. Open models such as Kimi K3, GLM 5.3, DeepSeek V4.1 Flash, and GLM 5.3 Flash now handle both complex architectural tasks and everyday fixes at a fraction of the per-token cost. A per-session router reads each session’s first task and routes it to either a fast, low-cost model or a frontier model; when no Anthropic key is provided it routes between GLM 5.3 and GLM 5.3 Flash, and Together AI serves the largest share of OpenRouter tokens for these models. Billing uses the existing Together API key with pay-as-you-go or credit packs, and a per-session tracker shows what the session would have cost on Opus 5.5.
Context
Engineering teams using coding agents on premium closed models face monthly costs ranging from tens of thousands to millions of dollars. Open models have meaningfully closed the gap, with leaders like Kimi K3 and GLM 5.3 handling many hard coding tasks at lower cost. Together Link addresses this by routing agent tasks to open models on Together AI without changing the agent or workflow.
Approach / What changed
Together Link installs via a single curl command and connects coding agents to Together AI. It supports Claude Code, Claude Desktop, Codex, OpenCode, and Pi. A per-session router reads the first task and sends it to the appropriate model: quick fixes to fast, low-cost models and hard problems to frontier models. When an Anthropic key is provided, it routes between Opus 5.5 and GLM 5.3; otherwise between GLM 5.3 and GLM 5.3 Flash. Billing uses the existing Together API key with pay-as-you-go or credit packs.
Takeaways
Together Link supports multiple coding agent harnesses including Claude Code, Claude Desktop, Codex, OpenCode, and Pi, requiring no workflow changes.
The per-session router assigns each session’s first task to either a fast low-cost model or a frontier model; without an Anthropic key it routes between GLM 5.3 and GLM 5.3 Flash.
Together AI serves the largest share of OpenRouter tokens for DeepSeek V4.1 Flash (40.8%), GLM 5.3 Flash (28.2%), and Kimi K3 (23.1%).
FAQ
How does Together Link decide which model to use?
It reads each session's first task and routes it: quick fixes go to fast, low-cost models, and hard problems get frontier capability. If you bring an Anthropic key, it routes between Opus 5.5 and GLM 5.3; without one, between GLM 5.3 and GLM 5.3 Flash. Routing happens once per session to preserve prompt caching.
Which coding agents does Together Link support?
It supports Claude Code, Claude Desktop, Codex (in the ChatGPT app and the CLI), OpenCode, and Pi. Setup requires one command and uses your existing Together AI API key.
How much does Together Link cost?
Billing runs on your existing Together API key against serverless pay-as-you-go or credit packs, with no separate contract. A per-session tracker shows what you spent versus what the same session would have cost on Opus 5.5, demonstrating over 50% savings.
Source and freshness
- Source
- together.ai
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.