Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / COHERE
Cohere multimodal embedding model for text, image and mixed text-image document retrieval, classification and clustering.
PRIMARY-SOURCE VERIFIED
Cohere documents a 128,000-token context window. Input modalities: text + image + PDF. Output: embedding. 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Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.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 continues to list embed-v4.0 in the current model catalog with text, image and mixed text/image (PDF) inputs and a 128K context length.
Cohere now lists Embed v5 variants as newer embedding models, but embed-v4.0 is not marked deprecated in the current official model table.
No current public numeric PAYG API token rate for embed-v4.0 was verified, so pricing remains not-published rather than inheriting a rate from another Embed generation.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Embed v4.0 since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 128,000 context · Not published max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head a81376cb9fe2…