Vercel AI SDK on AI models run in Europe

Create an OpenAI-compatible provider for Evanesca in the Vercel AI SDK and stream text, tools and embeddings from models in Europe. createOpenAICompatible({ name, baseURL, apiKey }) from @ai-sdk/openai-compatible.

Tool documentation read on 12 Oct 2026

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

Tool: Vercel AI SDK · Agent framework (TypeScript)
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. Create the provider

includeUsage is off by default: turn it on to get token counts in streams. Always pass the provider's model object — a bare string ID goes to the global provider, the Vercel AI Gateway unless you changed it.

TypeScript

// npm i ai @ai-sdk/openai-compatible
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { embed, streamText } from "ai";

const evanesca = createOpenAICompatible({
  name: "evanesca",
  baseURL: "https://evanesca.app/api/v1",
  apiKey: process.env.EVANESCA_API_KEY,
  includeUsage: true,
});

const result = streamText({
  model: evanesca("gemma-4-26b"), // not the bare string "gemma-4-26b"
  prompt: "Hello from Europe",
});

const { embedding } = await embed({
  model: evanesca.embeddingModel("bge-multilingual-gemma2"),
  value: "a sunny day",
});

Where these settings come from

These settings come from Vercel AI SDK'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

Tool calling, streamed or not, works with openai-compatible chat models and depends on the Evanesca model you pick.
Set supportsStructuredOutputs: true only for models that accept a json_schema response format.

Where your prompts go

The SDK calls baseURL from your own server. Only the bare-string shortcut goes to the Vercel AI Gateway, a US service.

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 Vercel AI SDK work with Evanesca?

Yes, through its base URL setting: createOpenAICompatible({ name, baseURL, apiKey }) from @ai-sdk/openai-compatible. These settings come from Vercel AI SDK'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 Vercel AI SDK?

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 Vercel AI SDK?

The SDK calls baseURL from your own server. Only the bare-string shortcut goes to the Vercel AI Gateway, a US service. 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