Cline on Flux
Cline translates every string, gets the tone checked, fixes what was flagged and opens a PR.
“Translate the app into six languages, check that the tone reads naturally, and open a PR.”
Examples. Names, prices and costs are illustrative.
Flux split the ask into jobs and sent each one to the model or tool that fits it. It picks among vetted models for each kind of task, cost-aware.
Translate 412 strings with QwenLive
Model
Bulk translation is steady, repetitive work, so Flux picked a fast multilingual model.
Check the tone with ClaudeLive
Model
Tone is judgement, so a frontier model read every language and flagged what sounded off.
Rework the 7 lines Claude flaggedLive
Model
Only the flagged lines went back for a rewrite, which keeps the cost down.
Open the pull request on GitHubShipping
Apps
The pull request went through the GitHub connection.
Result PR #88 adds French, German, Spanish, Italian, Portuguese and Japanese.
Every call comes back with the model or tool that ran it and what it cost, all on one bill.
These costs are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay its own rate. See pricing
Example receiptIllustrative
| Step | Cost |
|---|---|
| Translate 412 strings with QwenModel | $0.009 |
| Check the tone with ClaudeModel | $0.016 |
| Rework the 7 lines Claude flaggedModel | $0.001 |
| Open the pull request on GitHubApps | $0.010 |
| One bill | $0.036 |
One key, any agent. If it can talk to OpenAI or Anthropic, it can connect to Flux.
Translating is quick work for a fast model. Judging whether it sounds natural is harder, so Flux sends that to a stronger one, and only the lines it flags are redone.
Not yet. Apps on your own key are shipping. Until then, your agent can use its own tools for these steps, and Murage runs them today with apps built in. The steps marked Live work today.
The costs on this page are illustrative, not a quote. flux-auto bills each model step at the Standard rate, or the Fast rate when it sends the step to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay that model’s own rate instead. Web, image, voice and app steps have their own prices.
Agent use needs native tool calling. flux-auto resolves to models that support it.
One key for every model and tool in this example.