Hermes Agent with an uncensored model

Where the settings are

Settings live in ~/.hermes/config.yaml; secrets live in ~/.hermes/.env. Hermes reads CLI flags first, then config.yaml, then .env, then its defaults. A providers entry names its key variable with key_env, so the key never sits in config.yaml. Older guides show a custom_providers list; Hermes still reads it and hermes update migrates it, but new setups use the mapping below.

Steps

1. Create a key in the console, one for Hermes alone so its requests sit apart on the usage page, and put it in the env file, one line:

2. Add the provider to config.yaml. The ids under models are a starting list; any id on the models page goes in the same mapping:

3. Run hermes and send a message. The request shows on the console’s usage page within seconds, with its tokens and its charge.

The same block from the shell. Dotted paths go to config.yaml; the UPPER_SNAKE name goes to .env:

Switch inside a session with /model; the change lasts for that session unless --global writes it back to config.yaml:

What each setting does

api

https://api.uncensoredllm.ai/v1

the endpoint, with the /v1; base_url is accepted as an alias

key_env

UNCENSOREDLLM_API_KEY

the variable in .env that holds the whole sk-ullm- key

transport

chat_completions

the OpenAI chat format, which every build on the models page answers

default_model

glm-5.3-uncensored

the id this entry starts with

models

id: {}

per-model settings keyed by id; context_length under an id overrides what Hermes detects

model.provider

custom:uncensoredllm

selects the entry; model.default is the id Hermes starts with

Picking a model

Hermes needs tool calling for every file read, shell command and subagent, so before a long task on a new id send one short task and check that Hermes runs a tool. Input price decides the session cost, because Hermes sends the conversation and every tool result back on each turn. The cost column is one turn of 30,000 tokens in and 1,000 out at the catalog prices on 2026-11-09.

For coding specifically, the uncensored coding AI guide compares the code builds and costs a full coding day on each.

Check it

hermes status shows the model, the active provider and which providers have a credential, without printing key values. From the same shell, the key should list the models:

Then send one request the way Hermes does. -i prints the headers: x-uplink-request-id names the request, and on a non-streamed answer x-uplink-charge is what it cost in USD.

Errors and fixes

• 401 invalid_api_key: the key is wrong, revoked or not reaching the request. Check ~/.hermes/.env for the line, confirm key_env names the same variable, and copy the key again from the console.
• 402 insufficient_balance: the balance does not cover the request. Top up in the console. 402 monthly_limit_reached means the key hit the monthly spend limit you set on it.
• 404 model_not_found: the id in model.default is not on the models page. Copy the id from the page and set it with hermes config set model.default <id>.
• 429 rate_limited: the key hit its rate limit. The response carries retry-after.
• A 400 on the first run: Hermes’ own FAQ puts this down to a model name mismatch. Run hermes config show and compare model.default against the models page.
• Every custom endpoint is ignored: an old custom_providers key in config.yaml is no longer a YAML list. Move the entry to the providers mapping on this page, then run hermes doctor.

Sources

Field names follow Hermes Agent’s providers page and configuration guide, read 2026-11-06. Prices are from the live catalog at render.

Questions