Text Embedding 3 (Large) by OpenAI costs $0.130 per 1 Million input tokens and N/A (Vectors) per 1 Million output tokens. It features a 8k context window and has a blended 3:1 production rate of $0.098/1M tokens.
Text Embedding 3 (Large)
State-of-the-art 3072-dimension vector embedding model.
Verified Specifications & Benchmark Data
| Developer / Provider | OpenAI |
| Model Family | Embeddings |
| Blended 3:1 Rate (Production Benchmark) | $0.098 / 1M tokens |
| Batch API Discount (24hr SLA) | 50% off standard rate |
| Multimodal Vision | ❌ Text Only |
| Function Calling / Structured Outputs | ❌ Not Available |
| MMLU Benchmark Score | N/A (Specialized) |
| Latency & Throughput Tier | Fast |
| Optimal Architecture & Use Cases | Dense multilingual retrieval, legal/medical knowledge bases |
Frequently Asked Questions about Text Embedding 3 (Large)
How much does Text Embedding 3 (Large) cost per 1M tokens?
Text Embedding 3 (Large) pricing is set at $0.130 per 1 million input tokens and N/A (Vectors) per 1 million output tokens. For high-volume batch workloads, 24-hour batch queues provide a 50% off standard rate.
How much money does Text Embedding 3 (Large) prompt caching save?
Prompt caching is currently not natively offered for Text Embedding 3 (Large) on direct serverless endpoints.
What is the context window limit of Text Embedding 3 (Large)?
Text Embedding 3 (Large) has a maximum context window of 8k (8,191 tokens), supporting up to 4,096 completion tokens per response.
Direct Matchups with Text Embedding 3 (Large)
See how Text Embedding 3 (Large) compares against other leading frontier and open-weights models in cost and latency.
Compare OpenAI vs OpenAI pricing, context limits, and cost per 1M tokens.
Compare OpenAI vs Groq (Meta) pricing, context limits, and cost per 1M tokens.
Compare OpenAI vs Google pricing, context limits, and cost per 1M tokens.
Compare OpenAI vs Google pricing, context limits, and cost per 1M tokens.