Flux for Hermes

Keep Hermes. Give it 90+ models from 12 AI labs on one key, plus page reading and images through the Flux tools server.

Set it up

Point the model block at Flux as a custom provider. ~/.hermes/config.yaml

~/.hermes/config.yaml

model:
  provider: custom
  base_url: https://api.fluxrouter.ai/v1
  name: flux-auto
  api_key_env: FLUX_API_KEY

This recipe comes from our earlier Hermes guide. We have not re-checked it against the newest Hermes release yet.

Run hermes and send "Reply with the word ready."
Open Activity in your Flux account to see the call counted against the model that answered and the key that made it.

What Hermes gets through Flux
Ability	Today	How it reaches Hermes
Every major model	Live	Automatic, through the base URL.
Read a web page	Live	Add the Flux tools server (below).
Search the web	Rolling out	Switched on and being checked. Not promised yet.
Make images	Live	Add the Flux tools server (below).
Speak	Rolling out	Switched on and being checked. Not promised yet.
Transcribe audio	Not in agents yet	Live on the API for your own code. No agent reaches it yet.
Act in your apps	Shipping	Not live yet. It is on the way.
Memory	Shipping	Not live yet. It is on the way.
Second opinion	Rolling out	Switched on and being checked. Not promised yet.

Statuses come from the same record as the abilities on the homepage, so they change everywhere at once.

Page reading and image making reach Hermes through the Flux tools server, an MCP server on the same key. Web search joins it once it is live.

Add the Flux tools server to the same config, then restart Hermes. ~/.hermes/config.yaml

~/.hermes/config.yaml

mcp_servers:
  flux-tools:
    url: "https://api.fluxrouter.ai/mcp-tools/"
    headers:
      Authorization: "Bearer sk-YOUR-FLUX-KEY"

Format from Hermes’s own MCP docs, read on 28 September 2026.

Hermes reads the key from the variable named in api_key_env, so export FLUX_API_KEY in the shell you launch it from.
Keep the name set to flux-auto and Flux picks the lane for each request, or set flux-fast, flux-standard or flux-reasoning to pin a tier.
flux-auto bills at the Standard rate, or the Fast rate when it sends your request to the Fast lane and a Fast model answers. Never more than Standard. Pin a model and you pay that model’s rate instead.
Flux can pick a different model from one request to the next. A prompt cache belongs to one model, so a switch can mean a cache miss. If a long session leans on caching, pin a model.
The Flux tools server needs a funded key. Without one, its tools return an error instead of a result.

Hermes says no API key was found.: Hermes reads the variable named in api_key_env. Export FLUX_API_KEY in the same shell you start Hermes from, or add it to your shell profile.
Hermes returns a 404.: base_url must be the OpenAI-compatible base, ending in /v1 with nothing after it.
Every request comes back 401.: The key is missing, mistyped, or an old provider key is still set and wins. Paste your Flux key again and remove any other provider key from this config.
Requests come back 402.: Your account has reached its spend ceiling. Add funds or raise the ceiling in your Flux account, then try again.

Plan a trip

Find three hotels in Lisbon under €200 for next weekend, send the best to Sarah on Slack, and read me the summary.

Some steps in this job use abilities that are still shipping, so Hermes does part of it today.