AI Model Watch
Models / OpenAI

text-embedding-3-large

GA

Most capable embedding model. Output up to 3072 dimensions (reducible via dimensions param). Max input 8191 tokens (8191/3072 corroborated by OpenAI new-embedding-models announcement, not the model spec page). Embeddings have no output-token billing; $0.13/1M input.

Provider
OpenAI
Status
GA
Input price
$0.13 / 1M tokens
Output price
—
Cached input
—
Blended price
—
Context window
8,191 tokens (8K)
Max output
—
Modality
text
Knowledge cutoff
—
Released
25 Jan 2024
API string
text-embedding-3-large

Source: OpenAI official documentation ↗

See also

Compare text-embedding-3-large with…

text-embedding-3-large vs Claude Opus 4.8→

— vs $10 blended /M

text-embedding-3-large vs Claude Opus 4.7→

— vs $10 blended /M

text-embedding-3-large vs Claude Opus 4.6→

— vs $10 blended /M

text-embedding-3-large vs Claude Opus 4.5→

— vs $10 blended /M