OpenClaw on AI models run in Europe

Add Evanesca as a model provider in openclaw.json and run your self-hosted OpenClaw agents on open models run in Europe. models.providers in ~/.openclaw/openclaw.json with api: openai-completions; the default model in agents.defaults.model.primary.

Tool documentation read on 12 Oct 2026

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

Tool: OpenClaw · 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. Declare the provider

The Gateway reloads the file on the fly. Turn usage in streaming on: for an endpoint it does not know, OpenClaw leaves it off, which hides token counts and leaves compaction guessing. Evanesca ends every stream with a usage chunk, so the flag is safe.

~/.openclaw/openclaw.json

{
  agents: { defaults: { model: { primary: "evanesca/deepseek-v4.1-flash" } } },
  models: {
    mode: "merge",
    providers: {
      evanesca: {
        baseUrl: "https://evanesca.app/api/v1",
        apiKey: "${EVANESCA_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "deepseek-v4.1-flash",
            name: "DeepSeek V4.1 Flash",
            reasoning: true,
            input: ["text", "image"],
            contextWindow: 1000000,
            compat: { supportsUsageInStreaming: true },
          },
        ],
      },
    },
  },
}

Where these settings come from

These settings come from OpenClaw'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

OpenClaw acts through tools: stay on models whose tool calling is measured.
A model that reads images is declared with input: ["text", "image"]; otherwise attachments only travel as text references.
Models are addressed as provider/model — evanesca/deepseek-v4.1-flash — including with /model in a conversation.

Where your prompts go

OpenClaw is self-hosted: your Gateway calls the configured baseUrl itself, with no relay through OpenClaw's servers.

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 OpenClaw work with Evanesca?

Yes, through its base URL setting: models.providers in ~/.openclaw/openclaw.json with api: openai-completions; the default model in agents.defaults.model.primary. These settings come from OpenClaw'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 OpenClaw?

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 OpenClaw?

OpenClaw is self-hosted: your Gateway calls the configured baseUrl itself, with no relay through OpenClaw's servers. 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