Cohere logo

Rerank 3.5


Rerank 3.5 is Cohere's embedding model with a 4K context window and up to 4K output tokens, available from 2 providers, starting at $N/A / 1M input and $N/A / 1M output. Cohere's Rerank 3.5 model that improves search systems by sorting documents based on semantic similarity to a query.
Specifications
Canonical IDcohere-rerank-3-5
TypeEmbedding
StatusActive
CreatorCohereCohere
Providers
Context Window4K tokens
Max Output4K tokens
Input ModalitiesText
Output ModalitiesText
Release Date · 1 year ago

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Amazon Bedrock logo
Amazon Bedrock
cohere.rerank-v3-5:0
Azure AI Foundry logo
Azure AI Foundry
azure_ai/cohere-rerank-v3.5

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Rerank 4 Fast33K$2.00$0.000Available
Rerank 4 Pro33K$2.50$0.000Available
Rerank 3.54K$0.000$0.000Current
Voyage Rerank 3.532K$0.000$0.000Available
NV RerankQA Mistral 3 4BAvailable
Rerank 3 English4K$0.000$0.000Available
Rerank 3 Multilingual4K$0.000$0.000Available
Voyage Rerank 2.532K$0.050$0.000Available
Voyage Rerank 2.5 Lite32K$0.020$0.000Available
BGE Reranker M3 28K$0.010$0.010Available
Jina Reranker 2 Base Multilingual1K$0.018$0.018Available

Model IDs