goose on AI models run in Europe

Register Evanesca as a custom provider in goose, on the desktop or in the CLI, and run its extensions on models run in Europe. A JSON file in ~/.config/goose/custom_providers/, or Settings → Models → Configure providers → Add Custom Provider.

Tool documentation read on 12 Oct 2026

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

Tool: goose · Desktop and CLI 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. Write the provider file

In this file, base_url carries the whole chat-completions path. Give each model a context limit, or goose assumes 128,000 tokens. The key is read from the variable named in api_key_env.

~/.config/goose/custom_providers/evanesca.json

{
  "name": "evanesca",
  "engine": "openai",
  "display_name": "Evanesca",
  "api_key_env": "EVANESCA_API_KEY",
  "base_url": "https://evanesca.app/api/v1/chat/completions",
  "models": [
    { "name": "deepseek-v4.1-flash", "context_limit": 1000000 },
    { "name": "gemma-4-26b", "context_limit": 256000 }
  ],
  "supports_streaming": true,
  "requires_auth": true
}

2. Open a session

With the key exported, start goose on the provider; GOOSE_MODEL picks the model without the menu.

Shell

GOOSE_MODEL=deepseek-v4.1-flash goose session --provider evanesca

Where these settings come from

These settings come from goose'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

goose works through tool calls: with a model that does not make them, it can only chat, every extension idle.
Through the built-in OpenAI provider instead, host and path are set apart: OPENAI_HOST=https://evanesca.app and OPENAI_BASE_PATH=api/v1/chat/completions — otherwise requests get a 404.
Keys written in config.yaml are ignored: goose reads them from the keyring or the variable.

Where your prompts go

goose runs on your machine and calls the URL you configured; its anonymous usage data collection is off by default.

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 goose work with Evanesca?

Yes, through its base URL setting: A JSON file in ~/.config/goose/custom_providers/, or Settings → Models → Configure providers → Add Custom Provider. These settings come from goose'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 goose?

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 goose?

goose runs on your machine and calls the URL you configured; its anonymous usage data collection is off by default. 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