embed-v4.0
Coheredocs.cohere.com/docs/models
A model that allows for text and images to be classified or turned into embeddings
Updated 11 min ago · first seen 11 Sept 2026
model_01M294H977WY356NF4GP30KPYQ
- Context
- 128K tokens
- T1 · 11 min ago
Specification
- Family
- Embed
Source:Cohere — docs & blogT1observed 11 min agohigh
- Context window
- 128K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
- Modalities
- text, image
Source:Cohere — docs & blogT1observed 11 min agohigh
- Input modalities
- text, image
Source:Cohere — docs & blogT1observed 11 min agohigh
- Output modalities
- embedding
Source:Cohere — docs & blogT1observed 11 min agohigh
- API model id
- embed-v4.0
Source:Cohere — docs & blogT1observed 11 min agohigh
- Official page
Source:Cohere — docs & blogT1observed 11 min agohigh
- Embedding dimensions
- 256, 512, 1024, 1536
Source:Cohere — docs & blogT1observed 11 min agohigh
- Endpoints
- Embed, Embed Jobs
Source:Cohere — docs & blogT1observed 11 min agohigh
- Foundry model id
- cohere-embed-v-4-plan
Source:Cohere — docs & blogT1observed 11 min agohigh
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
12
Source tiers
T112
Freshest observation
11 min ago
Conflicts
None
Modalities
- Modalities
- textimage
- Input
- textimage
- Output
- embedding
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Yes
Cohere — docs & blog · T1
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 128K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
No benchmark results recorded
Current prices
No current prices recorded
Available through 1
Price history
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Familyfamily1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Embed | → current | current | Cohere — docs & blogT1 | high | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 128K tokens | → current | current | Cohere — docs & blogT1 | high | deterministic |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text, image | → current | current | Cohere — docs & blogT1 | high | deterministic |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text, image | → current | current | Cohere — docs & blogT1 | high | deterministic |
Output modalitiesmodalities_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| embedding | → current | current | Cohere — docs & blogT1 | high | deterministic |
API model idapi_model_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| embed-v4.0 | → current | current | Cohere — docs & blogT1 | high | deterministic |
Official pageofficial_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://docs.cohere.com/docs/models | → current | current | Cohere — docs & blogT1 | high | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| A model that allows for text and images to be classified or turned into embeddings | → current | current | Cohere — docs & blogT1 | high | deterministic |
Embedding dimensionsembedding_dimensions1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 256, 512, 1024, 1536 | → current | current | Cohere — docs & blogT1 | high | deterministic |
Endpointsendpoints1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Embed, Embed Jobs | → current | current | Cohere — docs & blogT1 | high | deterministic |
Foundry model idfoundry_model_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| cohere-embed-v-4-plan | → current | current | Cohere — docs & blogT1 | high | deterministic |
Visionvision1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | Cohere — docs & blogT1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Cohere — docs & blog | docs.cohere.com/docs/models.md | model_docs | T1· Official | 11 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.