Continue on AI models run in Europe

List Evanesca's models in Continue's config.yaml with provider openai and apiBase, for chat, edits and agent mode on models in Europe. ~/.continue/config.yaml: a models entry with provider: openai and apiBase; the key in ~/.continue/.env.

Tool documentation read on 12 Oct 2026

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

Tool: Continue · Coding assistant
API format: OpenAI-compatible (Chat Completions)
Base URL: https://evanesca.app/api/v1
Your prompts: Not stated by the publisher

Setup

1. Declare the model and its capabilities

Continue infers what a model can do from the provider and the model name, and an Evanesca model ID means nothing to it: list tool_use yourself, or agent mode stays greyed out. The IDE extensions do not see your shell variables, so the key lives in a .env file read through secrets.

~/.continue/config.yaml

name: Evanesca
version: 1.0.0
schema: v1
models:
  - name: DeepSeek V4.1 Flash (Evanesca)
    provider: openai
    model: deepseek-v4.1-flash
    apiBase: https://evanesca.app/api/v1
    apiKey: ${{ secrets.EVANESCA_API_KEY }}
    roles: [chat, edit, apply]
    capabilities: [tool_use]
    defaultCompletionOptions:
      contextLength: 1000000
      maxTokens: 8192
  - name: BGE Multilingual Gemma2 (Evanesca)
    provider: openai
    model: bge-multilingual-gemma2
    apiBase: https://evanesca.app/api/v1
    apiKey: ${{ secrets.EVANESCA_API_KEY }}
    roles: [embed]

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

Where these settings come from

These settings come from Continue'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

Autocomplete wants a fill-in-the-middle model on a completions endpoint; Evanesca serves chat completions, so leave autocomplete on another model.
The embedding entry (roles: [embed]) lets Continue search your codebase with vectors computed in Europe.
Anonymous telemetry goes to PostHog unless you turn Allow Anonymous Telemetry off.

Where your prompts go

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 Continue work with Evanesca?

Yes, through its base URL setting: ~/.continue/config.yaml: a models entry with provider: openai and apiBase; the key in ~/.continue/.env. These settings come from Continue'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 Continue?

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 Continue?

Continue's documentation does not say outright where requests leave from. Its configuration stays on your machine and its air-gapped guide works offline once telemetry is off, which points to direct calls; Continue's hosted agents are a separate product. 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