text-embedding-3-small
Summary
text-embedding-3-small is a proprietary language model from OpenAI, released on 25 Jan 2024. It accepts text and generates text, with a 8K-token context window and up to 2K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.02 per million input tokens and Free per million output tokens (OpenAI API), across 1 provider we track.
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 25 Jan 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 8K (8,191 tokens) [models.dev] |
| Max output | 2K tokens [models.dev] |
| Knowledge cutoff | Jan 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
text-embedding-3-small API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenAI API text-embedding-3-small | $0.02 | Free | – | 8K | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of text-embedding-3-small?
text-embedding-3-small has a context window of 8,191 tokens (8K) and can generate up to 1,536 tokens in a single response, according to models.dev.
How much does the text-embedding-3-small API cost?
Through OpenAI API, text-embedding-3-small costs $0.02 per million input tokens and Free per million output tokens. Prices last verified 4 Oct 2026.
Is text-embedding-3-small open source?
No. text-embedding-3-small is a proprietary model; OpenAI has not released its weights. It is available through APIs including OpenAI API.
When was text-embedding-3-small released?
OpenAI released text-embedding-3-small on 25 Jan 2024, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.