LlamaIndex on AI models run in Europe

Build LlamaIndex RAG pipelines and agents on models run in Europe with OpenAILike and OpenAILikeEmbedding pointed at Evanesca. OpenAILike(model, api_base, api_key, …) from llama-index-llms-openai-like.

Tool documentation read on 12 Oct 2026

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

Tool: LlamaIndex · RAG framework (Python)
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. The LLM and the embedding model

Two defaults get in the way: is_chat_model is False, which sends LlamaIndex to the legacy completions endpoint Evanesca does not serve, and context_window is 3,900 tokens. Set both, plus is_function_calling_model for agents.

Python

# pip install llama-index-llms-openai-like llama-index-embeddings-openai-like
import os
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

llm = OpenAILike(
    model="deepseek-v4.1-flash",
    api_base="https://evanesca.app/api/v1",
    api_key=os.environ["EVANESCA_API_KEY"],
    context_window=1000000,
    is_chat_model=True,
    is_function_calling_model=True,
)

embed_model = OpenAILikeEmbedding(
    model_name="bge-multilingual-gemma2",
    api_base="https://evanesca.app/api/v1",
    api_key=os.environ["EVANESCA_API_KEY"],
)

Where these settings come from

These settings come from LlamaIndex'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

One OpenAILike instance per model; the embedding class takes model_name, not model.
Pass allow_parallel_tool_calls=True to chat_with_tools and to agents. Otherwise LlamaIndex sends parallel_tool_calls: false, which OVHcloud's endpoints answered with HTTP 400 on 13 October 2026.
Set is_function_calling_model=True only for models whose tool calling is measured.

Where your prompts go

The library runs in your Python process and calls api_base itself; nothing in OpenAILike goes through LlamaCloud.

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 LlamaIndex work with Evanesca?

Yes, through its base URL setting: OpenAILike(model, api_base, api_key, …) from llama-index-llms-openai-like. These settings come from LlamaIndex'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 LlamaIndex?

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 LlamaIndex?

The library runs in your Python process and calls api_base itself; nothing in OpenAILike goes through LlamaCloud. 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