Hermes Agent on AI models run in Europe

Run Nous Research's Hermes Agent on a custom endpoint: Evanesca's base URL in config.yaml, open models run in Europe behind it. ~/.hermes/config.yaml: model.provider custom with base_url, default and key_env; or hermes model → Custom endpoint.

Tool documentation read on 12 Oct 2026

SoonOpening soon: what follows describes the service as it will work.

Tool: Hermes Agent · Personal agent
API format: OpenAI-compatible (Chat Completions)
Base URL: https://evanesca.app/api/v1
Your prompts: From your machine or server, straight to Evanesca

Setup

1. Set the custom endpoint

config.yaml decides the model and the endpoint. Keep the key in ~/.hermes/.env and name it with key_env. A named provider lets you list several models and switch in the middle of a conversation.

~/.hermes/config.yaml

model:
  provider: custom
  base_url: https://evanesca.app/api/v1
  default: deepseek-v4.1-flash
  key_env: EVANESCA_API_KEY
  context_length: 1000000

providers:
  evanesca:
    api: https://evanesca.app/api/v1
    key_env: EVANESCA_API_KEY
    transport: chat_completions
    default_model: deepseek-v4.1-flash
    models:
      deepseek-v4.1-flash: { context_length: 1000000 }
      gemma-4-26b: { context_length: 256000 }

# ~/.hermes/.env
# EVANESCA_API_KEY=<your Evanesca key>

2. Change model mid-conversation

/model custom:evanesca:gemma-4-26b moves to another declared model. Adding a provider or a key goes through hermes model, outside the conversation.

Where these settings come from

These settings come from Hermes Agent's official documentation, read on 12 Oct 2026. This guide has not been run against Evanesca yet: it will be checked when the API opens.

Which model to pick

Evanesca's models from which a real tool call came back at their operator. This guide uses DeepSeek V4.1 Flash and Gemma 4 26B, picked from the catalogue for their properties. Prices per million tokens, input / output, margin and VAT included.

Model ID	Operator and place	Context	Reasoning	Price
`mistral-large-4`	EU region of Mistral AI	512k	—	€2.5133 / €7.7246
`deepseek-v4.1-flash`	Germany (AKI.IO)	1M	Yes	€1.008 / €3.024
`glm-5.3`	Germany (AKI.IO)	512k	Yes	€3.024 / €9.24
`qwen3.8-27b`	Scaleway — Paris, France	256k	Yes	€1.008 / €5.544
`deepseek-v4-flash`	Scaleway — Paris, France	256k	Yes	€0.672 / €1.344
`apertus-v1.5-70b`	Switzerland (Infomaniak)	100k	—	€1.2936 / €4.62
`glm-5.2`	Scaleway — Paris, France	256k	Yes	€3.024 / €9.24
`qwen3.6-35b`	Scaleway — Paris, France	256k	Yes	€0.42 / €2.52
`gemma-4-26b`	Germany (AKI.IO)	256k	—	€0.168 / €0.84
`mistral-small-4-119b`	EU region of Mistral AI	256k	—	€0.2772 / €1.1088
`qwen3.5-397b`	Scaleway — Paris, France	250k	Yes	€1.008 / €6.048
`gpt-oss-120b`	Scaleway — Paris, France	—	Yes	€0.252 / €1.008
`qwen3-coder-30b`	Scaleway — Paris, France	256k	—	€0.336 / €1.344
`qwen3-235b`	Scaleway — Paris, France	250k	—	€1.26 / €3.78
`mistral-small-3.2`	Scaleway — Paris, France	—	—	€0.252 / €0.588
`llama-3.3-70b`	Scaleway — Paris, France	—	—	€1.512 / €1.512
`pixtral-12b`	Scaleway — Paris, France	128k	—	€0.336 / €0.336

Reasoning tokens are billed as output. Where each model runs and what its operator keeps: Models and Europe.

Good to know

Hermes needs tool calling and at least 64,000 tokens of context; a smaller window is refused at startup.
Side tasks (vision, summaries, titles, compression) use the main model unless told otherwise, so they reach Evanesca too.
Hermes sends reasoning_effort: medium when nothing is set; mark models that do not reason with supports_reasoning: false.

Where your prompts go

With a custom endpoint, Hermes sends requests to the configured URL with your key; Nous Portal routing only applies if you choose the Portal as provider.

On Evanesca's side, the model runs at a European operator, named with its place in the x-evanesca-operator and x-evanesca-location headers of every response, and Evanesca keeps no copy of prompts or answers — only the billing data of each call. What each operator keeps is set out in Models and Europe; the host of Evanesca's servers is named in the legal notice.

Sources

Official documentation, read on 12 Oct 2026:

Frequently asked questions

Does Hermes Agent work with Evanesca?

Yes, through its base URL setting: ~/.hermes/config.yaml: model.provider custom with base_url, default and key_env; or hermes model → Custom endpoint. These settings come from Hermes Agent's official documentation, read on 12 Oct 2026. This guide has not been run against Evanesca yet: it will be checked when the API opens.

Which Evanesca model should I use with Hermes Agent?

One whose tool calling is measured. This guide uses DeepSeek V4.1 Flash and Gemma 4 26B; the 17 candidates are in this page's table, with their context window and price.

Do my prompts stay in Europe with Hermes Agent?

With a custom endpoint, Hermes sends requests to the configured URL with your key; Nous Portal routing only applies if you choose the Portal as provider. On Evanesca's side, the model runs at a European operator, named with its place in the x-evanesca-operator and x-evanesca-location headers of every response, and Evanesca keeps no copy of prompts or answers — only the billing data of each call. What each operator keeps is set out in Models and Europe; the host of Evanesca's servers is named in the legal notice.

One key, and the tool runs on models in Europe.

Prepaid credit, no subscription: the same key works with every guide.

Get an API key All integrations