OpenAI: text-embedding-3-small
text-embedding-3-small is an embedding model from OpenAI released on Jan 25, 2024. It reads text and writes vectors, with a 8K token context window.
Show moreShow less
It costs $0.02 per million input tokens, with no charge for output.
5 providers serve it, including Azure, Vercel AI Gateway and Azure Cognitive Services.
- Modalities
- In / out price
- $0.02 / $0 per 1M
- Context
- 8K
- Max output
- 2K
- Released
- Jan 25, 2024
- Knowledge cutoff
- Jan 2024
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
text-embedding-3-small pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.02 / 1M tokens | |
|---|---|---|
| Output | $0 / 1M tokens |
text-embedding-3-small providers
5 providers serve it, including Azure, Vercel AI Gateway and Azure Cognitive Services. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| OpenAI First party | $0.02 | $0 | – | 8K | 2K |
| Azure | $0.02 | $0 | – | 8K | 2K |
| Vercel AI Gateway | n/a | n/a | – | 8K | 2K |
| Azure Cognitive Services | $0.02 | $0 | – | 8K | 2K |
| SAP AI Core | $0.02 | $0 | – | 8K | 2K |
What text-embedding-3-small costs per month
Pick a workload close to yours or type your own volumes.
Alternatives to text-embedding-3-small
Models that take the same inputs, closest in price, cheaper ones first.
Qwen3 Embedding 0.6B
Embeddings33K contextTurns text into vectors for search and retrieval. Served by 3 providers.
by qwenJun 3, 2025$0.01/M input tokens$0.01/M output tokens3 providers
Qwen 3 Embedding 4B
Embeddings32K contextTurns text into vectors for search and retrieval. Served by 3 providers.
by qwenJan 1, 2025$0.01/M input tokens3 providers
Qwen3 Embedding 8B
Embeddings33K contextTurns text into vectors for search and retrieval. Served by 8 providers.
by qwenJan 1, 2025$0.01/M input tokens8 providers
BAAI: BGE M3
Embeddings8K contextTurns text into vectors for search and retrieval. Served by 2 providers.
by baaiJan 30, 2024$0.01/M input tokens2 providers
Mistral Embed
Embeddings8K contextTurns text into vectors for search and retrieval. Served by 3 providers.
by mistralaiDec 11, 2023$0.10/M input tokens3 providers
OpenAI: text-embedding-ada-002
Embeddings8K contextTurns text into vectors for search and retrieval. Served by 4 providers.
by openaiDec 15, 2022$0.10/M input tokens4 providers
More from OpenAI
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 29, 2026$2/M input tokens$10/M output tokens2 providers
- Index 38.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 20261.05M context$0.10/M input tokens$0.50/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$0.10/M input tokens$0.50/M output tokens2 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens2 providers
text-embedding-3-small questions
How much does the text-embedding-3-small API cost?
$0.02 per million input tokens and $0 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of text-embedding-3-small?
8,191 tokens of input, and it can write up to 1,536 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve text-embedding-3-small?
5 providers serve it, including Azure, Vercel AI Gateway and Azure Cognitive Services. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Is text-embedding-3-small open source?
No. OpenAI serves it through an API only, so you cannot download the weights or host it yourself.
When was text-embedding-3-small released?
Jan 25, 2024, with training data up to Jan 2024.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on text-embedding-3-small?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting