update descriptions

msakande · msakande · commit ca275a56bafb · 2024-10-21T12:32:36.000-05:00
diff --git a/articles/ai-studio/how-to/deploy-models-cohere-embed.md b/articles/ai-studio/how-to/deploy-models-cohere-embed.md
@@ -37,6 +37,8 @@ Cohere Embed English is a multimodal (text and image) representation model used
 * Context window of the model is 512 tokens
 * Embed English accepts images as a base64 encoded data url
 
+Image embeddings consume a fixed number of tokens per image—1,000 tokens per image—which translates to a price of $0.0001 per image embedded. The size or resolution of the image doesn't affect the number of tokens consumed, provided the image is within the accepted dimensions, file size, and formats.
+ 
 
 # [Cohere Embed v3 - Multilingual](#tab/cohere-embed-v3-multilingual)
 
@@ -46,6 +48,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
 * Context window of the model is 512 tokens
 * Embed Multilingual accepts images as a base64 encoded data url
 
+Image embeddings consume a fixed number of tokens per image—1,000 tokens per image—which translates to a price of $0.0001 per image embedded. The size or resolution of the image doesn't affect the number of tokens consumed, provided the image is within the accepted dimensions, file size, and formats.
 
 ---
 
diff --git a/articles/machine-learning/how-to-deploy-models-cohere-embed.md b/articles/machine-learning/how-to-deploy-models-cohere-embed.md
@@ -421,6 +421,7 @@ Cohere Embed English is a multimodal (text and image) representation model used
 * Context window of the model is 512 tokens
 * Embed English accepts images as a base64 encoded data url
 
+Image embeddings consume a fixed number of tokens per image—1,000 tokens per image—which translates to a price of $0.0001 per image embedded. The size or resolution of the image doesn't affect the number of tokens consumed, provided the image is within the accepted dimensions, file size, and formats.
 
 # [Cohere Embed v3 - Multilingual](#tab/cohere-embed-v3-multilingual)
 
@@ -430,6 +431,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
 * Context window of the model is 512 tokens
 * Embed Multilingual accepts images as a base64 encoded data url
 
+Image embeddings consume a fixed number of tokens per image—1,000 tokens per image—which translates to a price of $0.0001 per image embedded. The size or resolution of the image doesn't affect the number of tokens consumed, provided the image is within the accepted dimensions, file size, and formats.
 
 ---
 
