>_Codex on Flux
Write the week’s release notes and tell the team
Codex turns a week of merged pull requests into release notes with a cover image, then publishes and announces them.
“Write release notes for everything merged this week, make a cover image, publish them and tell the team.”
- AppsShipping
- ModelLive
- ImagesLive
Murage
Read 14 merged pull requestsShipping$0.010- Summarise them with DeepSeek$0.006
- Make a cover image$0.030
Publish the notes to NotionShipping$0.010
Announce them in #generalShipping$0.010
Examples. Names, prices and costs are illustrative.
What Flux did, step by step
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.
Read 14 merged pull requestsShipping
Apps
Codex needed the week’s merged work, so Flux read the pull requests from GitHub.
Summarise them with DeepSeekLive
Model
Summarising is a light job, so Flux picked a fast, low-cost model.
Make a cover imageLive
Images
The cover image went to an image model, on the same key.
Publish the notes to NotionShipping
Apps
The notes were published through the Notion connection.
Announce them in #generalShipping
Apps
The announcement went to #general through the Slack connection.
Result Release notes for v2.4 are live on Notion and announced in #general.
The receipt
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 |
|---|---|
| Read 14 merged pull requestsApps | $0.010 |
| Summarise them with DeepSeekModel | $0.006 |
| Make a cover imageImages | $0.030 |
| Publish the notes to NotionApps | $0.010 |
| Announce them in #generalApps | $0.010 |
| One bill | $0.066 |
Run it with your own agent
- Get your key.
- Connect Codex to Flux with flux-auto as the model. Codex setup
- For page reading and images, add the Flux tools server to Codex’s MCP settings as a remote HTTP server at
https://api.fluxrouter.ai/mcp-tools/, with your Flux key as the bearer token (Authorization: Bearer sk-flux-…). It offersweb_fetchto read a page andimage_generateto make an image. - Ask it for the job in your own words, like the ask at the top.
What works today
- AppsShippingApps 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.
- ModelLiveModel steps work today, as soon as your agent points at Flux with flux-auto.
- ImagesLiveMaking and editing images works today.
Try it with another agent
One key, any agent. If it can talk to OpenAI or Anthropic, it can connect to Flux.
Questions
Can I pick the tone of the notes?
Yes. Put it in the ask, for example “short, plain and for customers”. The model that writes the summary follows it like any other instruction.
Does every step work on my key today?
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.
What will it cost me?
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.
Anything to know about Codex?
Codex only speaks the Responses API, so wire_api must be "responses". Flux serves it at the same base URL. The provider IDs openai, ollama and lmstudio are reserved. Use a custom ID such as flux.
More jobs your agent can do
Give your agent everything else.
One key for every model and tool in this example.