Embed v4.0
cohere-embed-v4-0
Last refreshed 2026-05-16. Next refresh: weekly.
Embed v4.0 is worth evaluating for general LLM work when its provider route and context window match the workload.
Decision context: Coding task fit, 1 tracked provider route, and research from 2026-01-01.
Use it for
- Teams evaluating general LLM work
- Workloads that can use a 128k context window
- Buyers comparing 1 tracked provider route
Do not use it for
- Strict JSON or tool-calling flows
Cheapest output
-
Microsoft Foundry per 1M tokens
Provider routes
1
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-01-01
Researched 137d ago
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Microsoft Foundry | $0.120 | - | ServerlessPartial |
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
Latest multimodal embedding model supporting text, images, and mixed content (e.g., PDFs). Embed v4.0 offers variable embedding dimensions (256, 512, 1024, 1536 default) and supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance). Ideal for semantic search, classification, and clustering across multimodal data.
Embed v4.0 has a 128K-token context window.
