Kilo Code on AI models run in Europe

Register Evanesca as a custom provider in kilo.jsonc: Kilo Code runs in VS Code, JetBrains or its CLI on models run in Europe. A provider entry in ~/.config/kilo/kilo.jsonc, read by the CLI, VS Code and JetBrains; or Settings → Providers → Custom provider.

Tool documentation read on 12 Oct 2026

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

Tool: Kilo Code · 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. Declare the provider and its models

For a model Kilo does not know, tool_call defaults to false and the limits to zero: the agent can no longer edit files and stops tracking its context. Set both. The {env:…} syntax only works in the global file.

~/.config/kilo/kilo.jsonc

{
  "$schema": "https://app.kilo.ai/config.json",
  "model": "evanesca/deepseek-v4.1-flash",
  "provider": {
    "evanesca": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://evanesca.app/api/v1",
        "apiKey": "{env:EVANESCA_API_KEY}"
      },
      "models": {
        "deepseek-v4.1-flash": {
          "name": "DeepSeek V4.1 Flash (Evanesca)",
          "tool_call": true,
          "limit": { "context": 1000000, "output": 16384 }
        }
      }
    }
  }
}

Where these settings come from

These settings come from Kilo Code'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 goes through the Kilo Gateway and only offers Kilo's own models: it cannot use Evanesca.
Kilo's BYOK page covers a fixed list of providers used through Kilo's platform; a custom provider is the way in.
Codebase indexing can use Evanesca's embeddings: indexing.provider "openai-compatible" with the same base URL and bge-multilingual-gemma2.

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 Kilo Code work with Evanesca?

Yes, through its base URL setting: A provider entry in ~/.config/kilo/kilo.jsonc, read by the CLI, VS Code and JetBrains; or Settings → Providers → Custom provider. These settings come from Kilo Code'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 Kilo Code?

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 Kilo Code?

The local client calls a custom provider with your key. Kilo's privacy notice says keys stay on your machine and prompts go to the provider you picked — autocomplete, through the Kilo Gateway, is the exception. 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