Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / COHERE
Cohere's current high-quality Rerank 4 variant for complex multilingual retrieval and semi-structured data ranking.
PRIMARY-SOURCE VERIFIED
Cohere documents a 32,768-token context window. Input modalities: text. Output: ranking. Pricing status: No direct Standard price published.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
No direct Standard price published.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
Cohere lists rerank-v4.0-pro as a latest Rerank model and recommends it for state-of-the-art quality and complex use cases.
Cohere documents a 32,768-token context length for Rerank 4.0.
The API reports billed search_units and Cohere states Rerank is priced by quantity of searches.
No current public PAYG numeric rate for Rerank 4 Pro was verified in the cited official pricing documentation, so pricing remains not-published rather than inheriting an older Rerank price.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Rerank 4 Pro since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 32,768 context · Not published max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head c70e6cd5a809…