Very long inputs
Choose Embed v5.0 Pro
Embed v5.0 Pro reads up to 128k tokens per request, against 8k for text-embedding-3-large.
Embed v5.0 Pro vs text-embedding-3-large: price, context and capabilities
Choose Embed v5.0 Pro for very long inputs and images as input; on the other points the two are level or the data is missing.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Embed v5.0 Pro reads more per request: 128k tokens against 8k.
- Only Embed v5.0 Pro offers vision.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Images as input
Choose Embed v5.0 Pro
Embed v5.0 Pro accepts images as input; text-embedding-3-large does not.
Specifications side by side
| Embed v5.0 Pro | text-embedding-3-large | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Category | Embeddings | Embeddings |
| Status | Generally available | Generally available |
| Headline price | No data | $0.13 / 1M tokens |
| Context window | 128k | 8k |
| Max output | No data | No data |
| Released | No data | January 2024 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision | No data |
| API model id | embed-v5.0-pro | text-embedding-3-large |
Frequently asked questions
Should I choose Embed v5.0 Pro or text-embedding-3-large?
Choose Embed v5.0 Pro for very long inputs and images as input; on the other points the two are level or the data is missing.
Which is cheaper, Embed v5.0 Pro or text-embedding-3-large?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Embed v5.0 Pro or text-embedding-3-large?
Embed v5.0 Pro reads more per request: 128k tokens against 8k.
What is the difference between Embed v5.0 Pro and text-embedding-3-large?
Embed v5.0 Pro is made by Cohere and text-embedding-3-large by OpenAI. A price comparison is not possible: one of them has no comparable published price. Embed v5.0 Pro reads more per request: 128k tokens against 8k. Only Embed v5.0 Pro offers vision.