Which AI model for RAG over your documents?
An assistant that answers from your documents (RAG): product documentation, procedures, knowledge base.
DeepSeek V4.1 Flash
- Index
- 154.9
- Price / M tokens
- €0.27 / €1.07
- Cost / 1 M
- ≈ €1,500
On the Pareto line, capability score of 155 at a low price: suited to the long passages read for each question.
See in the ranking →Qwen3.8 27B
- Index
- 149.4
- Price / M tokens
- Free (local)
Open weights under the Apache 2.0 license: with a local embedding model, neither documents nor questions leave your server.
See in the ranking →Claude Sonnet 5.5
- Index
- 165.0
- Price / M tokens
- €1.79 / €8.92
- Cost / 1 M
- ≈ €10,710
On the Pareto line, with one of the best capability scores: better at saying “I don't know” when the passages don't hold the answer.
See in the ranking →Why these choices
For RAG, quality depends first on retrieving the right passages (the embedding model and how documents are chunked), then on the model that writes the answer. Each question reads several thousand tokens: the input price matters more than the output price.
Take action
Private chat on your documents: Ollama, Qdrant, Open WebUI
docker-compose stack for a private chat on your documents: Ollama (model), Qdrant (vector database) and Open WebUI (interface).
BGE-M3 embeddings for RAG over long documents
BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+ languages, no prefix needed. MIT license.
nomic-embed-text embeddings locally with Ollama
nomic-embed-text for a 100% local English RAG with Ollama: 768 dimensions, long texts, search_query: / search_document: prefixes. Apache 2.0.
Data: Epoch AI index (CC BY 4.0), developers' official prices converted at the ECB rate, updated 2026-10-12 · AI model ranking: intelligence, benchmarks and price