Cohere Embed and Rerank vs Jina Embeddings and Reranker

Cohere Embed and Rerank

Rerank 4 Pro and Fast with 32K context and top_n, tracked per model on the status page. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.

Jina Embeddings and Reranker

jina-reranker-v3.5 (20 July 2026) with a 131,072-token window and no document cap. No price per token in any currency on the public pages.

Cohere Embed and Rerank

1. Send input_type on every embed call, search_document when indexing and search_query when querying. The endpoint rejects a call without it
2. Batch 96 inputs a call, the maximum, stay under 2,000 inputs a minute, and check every batch returns every embedding type you asked for (an open SDK bug drops types missing from the first response)
3. Budget rerank by searches. One query with up to 100 documents is one search, and a document over 500 tokens counts as several
4. Set max_tokens_per_doc on rerank. The default of 4,096 truncates long documents even on the 32K models
5. Ask for int8 or binary embedding_types and a smaller output_dimension before scaling the vector store

Jina Embeddings and Reranker

1. Send the whole candidate set to rerank in one call. The 131K window on v3.5 fits hundreds of chunks
2. On a 429, back off exponentially. Limits count per key when a key is sent, per IP otherwise
3. Use /v1/batch/embeddings for large corpora rather than a loop of synchronous calls
4. Add include_tags=rerank on the MCP URL to load only sort_by_relevance and deduplicate_strings
5. Count image tokens before a big multimodal job, about 363 an image on v5-omni