Very long inputs
Choose Embed v4.0
Embed v4.0 reads up to 128k tokens per request, against 8k for text-embedding-3-large.
Embed v4.0 vs text-embedding-3-large: price, context and capabilities
Choose Embed v4.0 for very long inputs, images as input and the latest release; 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 v4.0 reads more per request: 128k tokens against 8k.
- Embed v4.0 is the newer model (April 2025, against January 2024).
- Only Embed v4.0 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 v4.0
Embed v4.0 accepts images as input; text-embedding-3-large does not.
Latest release
Choose Embed v4.0
Embed v4.0 is the newer release (April 2025, against January 2024 for text-embedding-3-large).
Specifications side by side
| Embed v4.0 | text-embedding-3-large | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Category | Embeddings | Embeddings |
| Status | Legacy | Generally available |
| Headline price | No data | $0.13 / 1M tokens |
| Context window | 128k | 8k |
| Max output | No data | No data |
| Released | April 2025 | January 2024 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision | No data |
| API model id | embed-v4.0 | text-embedding-3-large |
Frequently asked questions
Should I choose Embed v4.0 or text-embedding-3-large?
Choose Embed v4.0 for very long inputs, images as input and the latest release; on the other points the two are level or the data is missing.
Which is cheaper, Embed v4.0 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 v4.0 or text-embedding-3-large?
Embed v4.0 reads more per request: 128k tokens against 8k.
What is the difference between Embed v4.0 and text-embedding-3-large?
Embed v4.0 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 v4.0 reads more per request: 128k tokens against 8k. Embed v4.0 is the newer model (April 2025, against January 2024). Only Embed v4.0 offers vision.
Which is newer, Embed v4.0 or text-embedding-3-large?
Embed v4.0 was released on April 2025 and text-embedding-3-large on January 2024.