You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/deploy-models-cohere-embed.md
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -231,6 +231,7 @@ Cohere Embed English is a multimodal (text and image) representation model used
231
231
* Context window of the model is 512 tokens
232
232
* Embed English accepts images as a base64 encoded data url
233
233
234
+
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.
@@ -240,6 +241,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
240
241
* Context window of the model is 512 tokens
241
242
* Embed Multilingual accepts images as a base64 encoded data url
242
243
244
+
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.
243
245
244
246
---
245
247
@@ -424,6 +426,7 @@ Cohere Embed English is a multimodal (text and image) representation model used
424
426
* Context window of the model is 512 tokens
425
427
* Embed English accepts images as a base64 encoded data url
426
428
429
+
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.
@@ -433,6 +436,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
433
436
* Context window of the model is 512 tokens
434
437
* Embed Multilingual accepts images as a base64 encoded data url
435
438
439
+
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.
Copy file name to clipboardExpand all lines: articles/machine-learning/how-to-deploy-models-cohere-embed.md
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,6 +37,7 @@ Cohere Embed English is a multimodal (text and image) representation model used
37
37
* Context window of the model is 512 tokens
38
38
* Embed English accepts images as a base64 encoded data url
39
39
40
+
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.
@@ -46,6 +47,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
46
47
* Context window of the model is 512 tokens
47
48
* Embed Multilingual accepts images as a base64 encoded data url
48
49
50
+
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.
49
51
50
52
---
51
53
@@ -228,6 +230,7 @@ Cohere Embed English is a multimodal (text and image) representation model used
228
230
* Context window of the model is 512 tokens
229
231
* Embed English accepts images as a base64 encoded data url
230
232
233
+
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.
@@ -237,6 +240,7 @@ Cohere Embed Multilingual is a multimodal (text and image) representation model
237
240
* Context window of the model is 512 tokens
238
241
* Embed Multilingual accepts images as a base64 encoded data url
239
242
243
+
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.
0 commit comments