rerank-2.5
cheaperInference/rerank-2.5
- Context window
- 32,000
- Maximum output
- 32,000
30 indexed models
30 matching models
cheaperInference/rerank-2.5
cheaperInference/rerank-2.5-lite
azureFoundry/azureml-voyage/rerank-2.5-lite@1
Reranker optimized for latency & quality. Context length: 32K for queries & docs (8K for queries).
azureFoundry/azureml-voyage/rerank-2.5-lite@2
Reranker optimized for latency & quality. Context length: 32K for queries & docs (8K for queries).
azureFoundry/azureml-voyage/rerank-2.5@1
Reranker optimized for quality. Context length: 32K for queries & docs (8K for queries).
cheaperInference/rerank-3
cheaperInference/rerank-3-lite
azureFoundry/azureml-voyage/rerank-3-lite@1
Reranker optimized for latency & quality. Context length: 32K for queries & docs (8K for queries).
azureFoundry/azureml-voyage/rerank-3-lite@2
Reranker optimized for latency & quality. Context length: 32K for queries & docs (8K for queries).
azureFoundry/azureml-voyage/rerank-3@1
Reranker optimized for quality. Context length: 32K for queries & docs (8K for queries).
azureFoundry/azureml-voyage/rerank-3@2
Reranker optimized for quality. Context length: 32K for queries & docs (8K for queries).
cheaperInference/voyage-3.5
azureFoundry/azureml-voyage/voyage-3.5-embedding-model@1
Voyage 3.5 is a state-of-the-art text embedding model that delivers superior retrieval quality for general-purpose and multilingual applications, outperforming OpenAI-v3-large by 8.26% on average while offering 2.2x lower costs. The model supports flexible
azureFoundry/azureml-voyage/voyage-3.5-embedding-model@2
Text embedding model optimized for general-purpose (including multilingual) retrieval/search and AI applications. 32K context length.
cheaperInference/voyage-3.5-lite
cheaperInference/voyage-3-large
cheaperInference/voyage-4
azureFoundry/azureml-voyage/voyage-4-embedding-model@1
Text embedding model optimized for general-purpose (including multilingual) retrieval/search and AI applications. 32K context length.
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.