Cohere Embed Models by Cohere
CohereProprietary
8 models2023–2025Up to 128k ctxFrom $0.1/1M input
Details
ResearcherCohere
LicenseProprietary
Commercial useCommercial use: conditional
Models8
Released2023–2025
Max context128k
Capabilities
Multimodal5 of 8 models
Links
WebsiteAbout
Cohere embedding models for semantic search, classification, and retrieval across text and multimodal inputs.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
8 in view
Cohere Embed v4.0Current
Use when the workload needs embedding, 128k context, and multimodal inputs.
2025-04embedding128k contextmultimodal inputs
Cohere Embed EnglishCurrent
Use when provider availability and model metadata match the workload.
2024-01
Cohere Embed MultilingualCurrent
Use when provider availability and model metadata match the workload.
2024-01
Cohere Embed English v3.0Current
Use when the workload needs embedding, 512 context, and multimodal inputs.
2023-11embedding512 contextmultimodal inputs
Use when the workload needs embedding, 512 context, and multimodal inputs.
2023-11embedding512 contextmultimodal inputs
Use when the workload needs embedding, 512 context, and multimodal inputs.
2023-11embedding512 contextmultimodal inputs
Use when the workload needs embedding, 512 context, and multimodal inputs.
2023-11embedding512 contextmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Cohere Embed v4.0 | Use when the workload needs embedding, 128k context, and multimodal inputs. | 2025-04 | embedding128k contextmultimodal inputs | Current |
| Cohere Embed v4 | Use when provider availability and model metadata match the workload. | 2024-06 | — | Current |
| Cohere Embed English | Use when provider availability and model metadata match the workload. | 2024-01 | — | Current |
| Cohere Embed Multilingual | Use when provider availability and model metadata match the workload. | 2024-01 | — | Current |
| Cohere Embed English v3.0 | Use when the workload needs embedding, 512 context, and multimodal inputs. | 2023-11 | embedding512 contextmultimodal inputs | Current |
| Cohere Embed English Light v3.0 | Use when the workload needs embedding, 512 context, and multimodal inputs. | 2023-11 | embedding512 contextmultimodal inputs | Current |
| Cohere Embed Multilingual v3.0 | Use when the workload needs embedding, 512 context, and multimodal inputs. | 2023-11 | embedding512 contextmultimodal inputs | Current |
| Cohere Embed Multilingual Light v3.0 | Use when the workload needs embedding, 512 context, and multimodal inputs. | 2023-11 | embedding512 contextmultimodal inputs | Current |
Release Timeline
4 release groups2025-04
1 current
Cohere Embed v4.0
Currentembedding128k contextmultimodal inputs
2024-06
1 current
Current
2024-01
2 current
Current
Current
2023-11
4 current
Cohere Embed English Light v3.0
Currentembedding512 contextmultimodal inputs
Cohere Embed English v3.0
Currentembedding512 contextmultimodal inputs
Cohere Embed Multilingual Light v3.0
Currentembedding512 contextmultimodal inputs
Cohere Embed Multilingual v3.0
Currentembedding512 contextmultimodal inputs
Specifications(8 models)
| Model | Released | Context | Multimodal |
|---|---|---|---|
| Cohere Embed v4.0 | 2025-04 | 128k | Yes |
| Cohere Embed v4 | 2024-06 | — | No |
| Cohere Embed English | 2024-01 | — | No |
| Cohere Embed Multilingual | 2024-01 | — | No |
| Cohere Embed English v3.0 | 2023-11 | 512 | Yes |
| Cohere Embed English Light v3.0 | 2023-11 | 512 | Yes |
| Cohere Embed Multilingual v3.0 | 2023-11 | 512 | Yes |
| Cohere Embed Multilingual Light v3.0 | 2023-11 | 512 | Yes |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Cohere Embed English v3.0 | Microsoft Foundry | $0.1 | — | Serverless |
| Cohere Embed Multilingual v3.0 | Microsoft Foundry | $0.1 | — | Serverless |
| Cohere Embed v4.0 | Microsoft Foundry | $0.12 | — | Serverless |
| Cohere Embed v4.0 | Vercel AI Gateway | $0.12 | — | Serverless |
Frequently Asked Questions
- What is Cohere Embed used for?
- Cohere Embed is used for embedding and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does Cohere Embed compare to Command?
- Cohere Embed by Cohere is strongest where you need embedding, while Command by Cohere is the closest related family to check for multilingual. Cohere Embed has 8 listed variants and reaches up to 128k context, while Command reaches up to 256k context, so compare the specs and pricing tables before choosing a production model.
- Which Cohere Embed model should I use?
- For the lowest listed input price, start with Cohere Embed English v3.0 through Microsoft Foundry at $0.1/1M input tokens. For the most capable/latest local choice, evaluate Cohere Embed v4.0 with 128k context and multimodal inputs.
Related Model Families
Models(8)
Cohere Embed v4.0
2025-04128k3 providers
Multimodal
Cohere Embed v4
2024-061 provider
Cohere Embed English
2024-011 provider
Cohere Embed Multilingual
2024-011 provider
Cohere Embed English v3.0
2023-115122 providers
Multimodal
Cohere Embed English Light v3.0
2023-115121 provider
Multimodal
Cohere Embed Multilingual v3.0
2023-115122 providers
Multimodal
Cohere Embed Multilingual Light v3.0
2023-115121 provider
Multimodal