openai·embedding

text-embedding-3-large

openai/text-embedding-3-large

OpenAI's large embedding model — 3072-dim, very strong semantic search.

At a glance

  • · $0.13 input / $0.00 output per 1M tokens (provider list price, billed in credits)
  • · Context window: 8,191 tokens
  • · OpenAI-compatible — model: "openai/text-embedding-3-large" (provider: openai)
  • · Best for: 3072 dimensions — top accuracy on MTEB benchmarks

Strengths

  • +3072 dimensions — top accuracy on MTEB benchmarks
  • +Dimension can be shortened via API (Matryoshka) — save storage without re-embedding
  • +Multilingual, strong on cross-language retrieval

Weaknesses

  • Pricier than 3-small, often with no noticeable quality edge on small corpora
  • Full 3072-dim is storage-intensive

Use cases

  • Semantic search over large knowledge bases
  • High-quality RAG pipelines
  • Cross-language retrieval (e.g. English query over German corpus)

Alternatives in the catalog

How to call it

Drop-in OpenAI-compatible. Just swap the `model` string and you're using this model.

curl https://www.getmorecredits.com/v1/embeddings \
  -H "Authorization: Bearer $GMC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/text-embedding-3-large",
    "input": "GetMoreToken: one API for 230+ AI models."
  }'

Good for

Frequently asked questions

How much does text-embedding-3-large cost?

Input is $0.13 per million tokens; output is $0.00 per million tokens — provider list price. On getmorecredits.com you pay in credits, no subscription, no minimum spend.

What's the context window of text-embedding-3-large?

text-embedding-3-large accepts up to 8,191 input tokens. That fits long conversations and medium documents into a single call.

Is text-embedding-3-large OpenAI-compatible?

Yes. On getmorecredits.com you call text-embedding-3-large with the same request shape as OpenAI: POST /v1/embeddings with "model": "openai/text-embedding-3-large". Existing OpenAI SDKs (Python, Node, etc.) work by changing the base URL and API key.