AI Model Watch
Models / Cohere

Embed 4 (embed-v4.0)

GA

Multimodal embedding model: text, images, PDFs. 128k context; output dimensions configurable 256-1536. Embedding model so no output-token price. Price $0.12 per 1M text input tokens; image embeddings ~$0.47 per 1M image tokens (per metacto/eesel/pecollective 2026). Embedding models have no 'output token' concept; image price recorded in notes only. Knowledge cutoff/release date not published in docs.

Provider
Cohere
Status
GA
Input price
$0.12 / 1M tokens
Output price
—
Cached input
—
Blended price
—
Context window
128,000 tokens (128K)
Max output
—
Modality
text, image
Knowledge cutoff
—
Released
—
API string
embed-v4.0

Source: Cohere official documentation ↗

See also

Compare Embed 4 (embed-v4.0) with…

Embed 4 (embed-v4.0) vs Claude Opus 4.8→

— vs $10 blended /M

Embed 4 (embed-v4.0) vs Claude Opus 4.7→

— vs $10 blended /M

Embed 4 (embed-v4.0) vs Claude Opus 4.6→

— vs $10 blended /M

Embed 4 (embed-v4.0) vs Claude Opus 4.5→

— vs $10 blended /M