Aider on AI models run in Europe

Run Aider, the pair programmer of the terminal, on models run in Europe: two environment variables and the openai/ prefix. OPENAI_API_BASE and OPENAI_API_KEY, or openai-api-base and openai-api-key in .aider.conf.yml.

Tool documentation read on 12 Oct 2026

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

Tool: Aider · Coding 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. Point Aider at Evanesca

Put openai/ before the Evanesca model ID so Aider sends it to the OpenAI-compatible base URL. Name a weak model too: it writes commit messages and summaries — here Gemma 4 26B.

Shell

export OPENAI_API_BASE=https://evanesca.app/api/v1
export OPENAI_API_KEY=$EVANESCA_API_KEY
aider --model openai/deepseek-v4.1-flash --weak-model openai/gemma-4-26b

2. Give it diff edits and the context window

With a model it does not know, Aider rewrites whole files: slow, and every rewritten line is billed. Two small files, next to your project or in your home directory, switch it to diff edits and tell it the window. Zero costs keep Aider from printing estimates in dollars that do not match Evanesca's prices.

.aider.model.settings.yml + .aider.model.metadata.json

# .aider.model.settings.yml
- name: openai/deepseek-v4.1-flash
  edit_format: diff

# .aider.model.metadata.json
{ "openai/deepseek-v4.1-flash": { "max_input_tokens": 1000000, "max_output_tokens": 16384,
    "input_cost_per_token": 0, "output_cost_per_token": 0,
    "litellm_provider": "openai", "mode": "chat" } }

Where these settings come from

These settings come from Aider'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

Aider applies edits from text formats it reads in the answer, not from tool calls: models without measured tool calling can work too.
The warning « Unknown context window size and costs » is harmless; the metadata file silences it.

Where your prompts go

Aider calls the API from your machine. Its analytics are opt-in and, according to its documentation, never include code, chats or keys.

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 Aider work with Evanesca?

Yes, through its base URL setting: OPENAI_API_BASE and OPENAI_API_KEY, or openai-api-base and openai-api-key in .aider.conf.yml. These settings come from Aider'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 Aider?

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 Aider?

Aider calls the API from your machine. Its analytics are opt-in and, according to its documentation, never include code, chats or keys. 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