AI Rate Card

RAG indexing cost calculator

What document search for an AI assistant (RAG) costs in embeddings and reranking: your documents embedded once, the changed share every month, the queries, and the passages reranked - at the cheapest seller of every model. How to use it

Documents: 6 000 000 tokens. Every month: 1 500 000 tokens to embed and 258 000 000 tokens to rerank.

Embedding models

ModelProviderPer 1M tokensIndex onceA month
Qwen3-Embedding-0.6B-batchdeepinfra$0.005$0.03$0.0075
BGE Base EN v1.5deepinfra$0.005$0.03$0.0075
E5 Base v2deepinfra$0.005$0.03$0.0075
all-MiniLM-L12-v2deepinfra$0.005$0.03$0.0075
all-MiniLM-L6-v2deepinfra$0.005$0.03$0.0075
all-mpnet-base-v2deepinfra$0.005$0.03$0.0075
CLIP ViT-B-32deepinfra$0.005$0.03$0.0075
CLIP ViT-B-32 Multilingual v1deepinfra$0.005$0.03$0.0075
multi-qa-mpnet-base-dot-v1deepinfra$0.005$0.03$0.0075
paraphrase-MiniLM-L6-v2deepinfra$0.005$0.03$0.0075
text2vec-base-chinesedeepinfra$0.005$0.03$0.0075
GTE Basedeepinfra$0.005$0.03$0.0075
qwen-embedding-0.6b (under review)daoxe$0.0072$0.0432$0.0108
pplx-embed-context-v1-0.6bperplexity$0.008$0.048$0.012
Qwen3 Embedding 0.6Bdeepinfra$0.01$0.06$0.015
Qwen3 Embedding 4Bhuggingface$0.01$0.06$0.015
Qwen3-Embedding-4B-batchdeepinfra$0.01$0.06$0.015
Qwen3 Embedding 8Bdeepinfra$0.01$0.06$0.015
BGE EN ICLdeepinfra$0.01$0.06$0.015
BGE Large EN v1.5deepinfra$0.01$0.06$0.015
BGE M3ovhcloud$0.01$0.06$0.015
bge-m3-multideepinfra$0.01$0.06$0.015
bge-m3-multi-8kdeepinfra$0.01$0.06$0.015
BGE Multilingual Gemma2ovhcloud$0.01$0.06$0.015
E5 Large v2deepinfra$0.01$0.06$0.015

Rerank models

Counted: embedding the documents once, re-embedding the changed share and every query each month, reranking the passages of every query. Not counted: the vector database, storage, and the answer model that writes from the passages - price it in the cost calculator or the coding agent calculator.

← Tools: pick a model by cost