rerank-english-v3.0
Coheredocs.cohere.com/docs/models
A model that allows for re-ranking English Language documents and semi-structured data (JSON). This model has a context length of 4096 tokens.
Updated 33 min ago · first seen 11 Sept 2026
model_01M294H994CJ106023YWH5QBG1
- Context
- 4K tokens
- T1 · 33 min ago
Specification
- Family
- Rerank
Source:Cohere — docs & blogT1observed 33 min agohigh
- Context window
- 4K tokens
Source:Cohere — docs & blogT1observed 33 min agohigh
- Modalities
- text
Source:Cohere — docs & blogT1observed 33 min agohigh
- Input modalities
- text
Source:Cohere — docs & blogT1observed 33 min agohigh
- API model id
- rerank-english-v3.0
Source:Cohere — docs & blogT1observed 33 min agohigh
- Official page
Source:Cohere — docs & blogT1observed 33 min agohigh
- Endpoints
- Rerank
Source:Cohere — docs & blogT1observed 33 min agohigh
- Foundry model id
- Cohere-rerank-v3-english
Source:Cohere — docs & blogT1observed 33 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
10
Source tiers
T110
Freshest observation
33 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
No
Cohere — docs & blog · T1
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 4K tokens
Source:Cohere — docs & blogT1observed 33 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 · Input modalities
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → 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 | 33 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.