Skip to content
InferenceHub

Embeddings & rerank

For RAG pipelines the gateway serves the OpenAI Embeddings API at POST /v1/embeddings and a reranker at POST /v1/rerank, on the same key as everything else.

Embeddings

input takes a string or an array of up to 2048 strings:

curl https://app.inferencehub.tech/v1/embeddings \
  -H "Authorization: Bearer sk-prov-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bge-m3", "input": ["the quick brown fox", "pack my box"]}'

Live embedding models (input-only billing, per 1M tokens): all-mini-lm-l6-v2 $0.009 · multi-qa-mpnet-base-dot-v1 $0.009 · bge-m3 $0.02 · e5-large-v2 $0.02 · qwen3-embedding-0.6b $0.04 · gte-large-en-v1.5 $0.09.

Rerank

Re-score retrieved passages: query plus up to 150 documents, returning results[].{index, relevance_score}:

curl https://app.inferencehub.tech/v1/rerank \
  -H "Authorization: Bearer sk-prov-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-reranker-v2-m3",
    "query": "how do I top up my balance?",
    "documents": ["Top up with card or crypto.", "Models are served at parity."]
  }'

Rerank serves bge-reranker-v2-m3 at $0.01/1M tokens, input-only.