Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / COHERE
Rerank 4 Fast
verified model reference.
Low-latency Rerank 4 variant for high-throughput multilingual retrieval and semi-structured data ranking.
32,768context tokens
Not publishedmax output
2026-10-07last verified
PRIMARY-SOURCE VERIFIED
Rerank 4 Fast at a glance.
Cohere documents a 32,768-token context window. Input modalities: text. Output: ranking. Pricing status: No direct Standard price published.
MODEL IDrerank-v4.0-fast
CONTEXT WINDOW32,768tokens
MAX OUTPUTNot published
KNOWLEDGE CUTOFFNot published
STANDARD RATENot publishedper search unit
OUTPUT RATE—not-published
CAPABILITY CONTRACT
Published model behavior.
text
Input modalities come from the cited official model documentation.
ranking
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
No direct Standard price published.
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
What the source record does not assume.
01
Cohere lists rerank-v4.0-fast as a latest Rerank model with 32,768-token context.
02
The API bills in search_units; no current public numeric PAYG search-unit rate was verified.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
Rerank 4 Fast: what changed.
No post-baseline factual changes recorded for Rerank 4 Fast since 2026-10-07.
VERIFIED BASELINE2026-10-07Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
Rerank 4 Fast verified history.
Rerank 4 Fast
Baseline verified: 32,768 context · Not published max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 8e73a9cb15ea…