Use open modelsin Claude Code
Use frontier open models in the harnesses you love at a fraction of the price.
Type one command. That's the whole setup.
Real sessions, seconds each: the short command launches your own agent on an open model, and prints the cost when you leave.
Your own Claude Code, signed in as you, launched on Auto. The whole Together lineup is one /model away.
Per-run settings evaporate on exit. Nothing to put back.
Claude Code stays signed in. Subscriptions stay yours.
Proxied sessions print their token and dollar totals.
Set the model to Auto.
The router weighs every task on its way through. Quick work rides GLM 5.3 Flash for pennies; the hard problems get Opus 5, and the receipt shows both.
Claude Code now. Eight more on the way.
tclaude is ready today. The rest of the board is coming soon.
Claude Code
fully supportedA local proxy translates Claude Code's traffic to Together. You stay signed in, and the session prints its cost on exit.
- Your Claude Code login and subscription
- ~/.claude settings, memory, and history
- Web search, via an optional Exa key
Five models, priced in the open.
Kimi K3 is the default; pick a model and an agent to compose the exact run.
tclaudeDrag your hours; the receipt reprints for Kimi K3.
From install to routed in ninety seconds.
- Run the installer
One paste. Everything lands in
~/.togetherlinkand keeps itself current. - Launch an agent
tclaude,tcodex,topencode. First launch asks once for your Together API key. - Work as usual
Same tool, open model. The receipt prints what the session cost.
TogetherLink versus doing it by hand.
You could export the keys and edit every agent's config yourself. The difference shows up the day you want your old setup back.
Common questions, short answers.
Longer ones live in the official docs and the LLM docs, which your agent can read on its own.
Does it touch my agent config?
No. Claude Code and Codex go through a local proxy; the other agents get per-run config that is gone on exit. The one exception is ChatGPT Desktop: patched once, backed up first, restored exactly.
Do I need the agent CLIs installed?
Yes, except DeepSeek Harness, which installs itself on first launch. Anything else missing, togetherlink prints the official install command and exits.
What does it cost?
TogetherLink is free and MIT licensed. You pay Together per token, at the prices above; proxied runs print the session total on exit.
How do I pick a model?
Put --model before the harness name; after it, flags belong to the agent. Kimi K3 is the default.
$ togetherlink --model zai-org/GLM-5.3 claudeWhat does it run on?
macOS and Linux. Everything lands in ~/.togetherlink/bin, with Bun brought along if you need it.
What is the daemon?
The local proxy for Claude Code and Codex traffic. It starts on demand and registers at login; daemon uninstall removes that.
$ togetherlink daemon statusHow do updates work?
The binary keeps itself current on its own. One command forces it right now.
$ togetherlink updateWhat about telemetry?
Anonymous usage analytics tied to a random install ID. One environment variable turns it off completely.
$ export TOGETHERLINK_TELEMETRY_DISABLED=1Your next session is one command away.
Free and MIT licensed · macOS and Linux · works with your Together API key