text-embedding-3-small pricing
text-embedding-3-small from OpenAI — embeddings API at $0.020 per 1M tokens, 1536 dimensions, 8,191-token max input. Cheap default; Matryoshka — shorten dimensions to save storage.
text-embedding-3-smallBilled per input token · prices USD, last verified 2026-06-27.
text-embedding-3-small cost calculator
Estimate the bill for embedding a corpus. Enter total tokens (≈ words × 1.3).
Re-embedding on model changes repeats this cost. Compare all models on the embeddings pricing page.
text-embedding-3-small vs other embedding models
Cost per 1M tokens, cheapest first — text-embedding-3-small highlighted.
| Model | Provider | Per 1M | Dimensions | Max input |
|---|---|---|---|---|
| BGE-M3open | BAAI | $0.010 | 1024 | 8K |
| Jina Embeddings v3 | Jina AI | $0.020 | 1024 | 8K |
| text-embedding-3-small | OpenAI | $0.020 | 1536 | 8K |
| Voyage-3.5 | Voyage AI | $0.060 | 1024 | 32K |
| Mistral Embed | Mistral | $0.100 | 1024 | 8K |
| Cohere Embed v4 | Cohere | $0.120 | 1536 | 128K |
| text-embedding-3-large | OpenAI | $0.130 | 3072 | 8K |
| Gemini Embedding | $0.150 | 3072 | 2K |
How text-embedding-3-small pricing works
text-embedding-3-small bills per input token at $0.020 per million — there are no output tokens, since the response is a fixed 1536-dimension vector. Cost scales only with how much text you embed, so the levers are corpus size and how often you re-embed. The batch endpoint halves the price to $0.010 per 1M for non-urgent jobs.
Higher dimensions improve retrieval marginally but increase vector-database storage and query cost proportionally — many models (including this one where noted) support shortening dimensions to trade a little accuracy for big storage savings.
text-embedding-3-small pricing FAQ
How much does text-embedding-3-small cost?
text-embedding-3-small costs $0.020 per 1M input tokens ($0.010 on the batch endpoint). Embedding 1 million typical documents of ~500 tokens each (500M tokens) would cost about $10.00.
How many dimensions does text-embedding-3-small output?
text-embedding-3-small returns 1536-dimension vectors, and supports Matryoshka shortening to smaller dimensions to cut storage. Its max input is 8,191 tokens per request.
Is there a cheaper embedding model than text-embedding-3-small?
Yes — BGE-M3 (BAAI) is cheaper at $0.010 per 1M tokens. The cheapest tracked here is BGE-M3 at $0.010.