Model Overview
text-embedding-3-large is our most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
Key Features
- High performance (3/4 dots rating)
- Slow speed (2/5 lightning bolts rating)
- Most capable embedding model
- Text input and output support
- Batch API and Embeddings endpoint support
Technical Specifications
- Pricing: $0.13 per 1M tokens
- Supports: Input: text only; Output: text only
- Features: Batch API support, Embeddings endpoint support
Snapshots
Positioning and Use Cases
text-embedding-3-large is our most capable embedding model for both english and non-english tasks. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
Rate Limits
- Free tier: 100 RPM, 2,000 RPD, 40,000 TPM
- Tier 1: 3,000 RPM, 1,000,000 TPM, 3,000,000 batch queue limit
- Tier 2: 5,000 RPM, 1,000,000 TPM, 20,000,000 batch queue limit
- Tier 3: 5,000 RPM, 5,000,000 TPM, 100,000,000 batch queue limit
- Tier 4: 10,000 RPM, 5,000,000 TPM, 500,000,000 batch queue limit
- Tier 5: 10,000 RPM, 10,000,000 TPM, 4,000,000,000 batch queue limit
Documentation
Official Documentation
