Skip to content

Commit b962301

Browse files
mchencomchenco
committed
new models and pricing page
1 parent 7ac058b commit b962301

File tree

6 files changed

+89
-57
lines changed

6 files changed

+89
-57
lines changed

‎src/content/docs/workers-ai/platform/pricing.mdx‎

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,10 @@ Neurons are our way of measuring AI outputs across different models, representin
5555
| @cf/baai/bge-small-en-v1.5 | $0.020 per M input tokens | 1841 neurons per M input tokens |
5656
| @cf/baai/bge-base-en-v1.5 | $0.067 per M input tokens | 6058 neurons per M input tokens |
5757
| @cf/baai/bge-large-en-v1.5 | $0.204 per M input tokens | 18582 neurons per M input tokens |
58+
|@cf/baai/bge-m3 |$0.012 per M input tokens|1075 neurons per M input tokens |
59+
|@cf/baai/bge-reranker-base |$0.003 per M input tokens|283 neurons per M input tokens |
5860
| @cf/meta/m2m100-1.2b | $0.342 per M input tokens <br/> $0.342 per M output tokens | 31050 neurons per M input tokens <br/> 31050 neurons per M output tokens |
5961
| @cf/microsoft/resnet-50 | $2.51 per M images | 228055 neurons per M images |
6062
| @cf/openai/whisper | $0.0005 per audio minute | 41.14 neurons per audio minute |
63+
|@cf/openai/whisper-large-v3-turbo|$0.0005 per audio minute |46.63 neurons per audio minute |
64+
|@cf/myshell-ai/melotts |$3.416 per M input tokens|310577 neurons per M input tokens|

‎src/content/workers-ai-models/bge-m3.json‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
{
2+
"id": "eed32bc1-8775-4985-89ce-dd1405508ad8",
3+
"source": 1,
4+
"name": "@cf/baai/bge-m3",
5+
"description": "Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.",
6+
"task": {
7+
"id": "0137cdcf-162a-4108-94f2-1ca59e8c65ee",
8+
"name": "Text Embeddings",
9+
"description": "Feature extraction models transform raw data into numerical features that can be processed while preserving the information in the original dataset. These models are ideal as part of building vector search applications or Retrieval Augmented Generation workflows with Large Language Models (LLM)."
10+
},
11+
"tags": [],
12+
"properties": [],
13+
"schema": {}
14+
}

‎src/content/workers-ai-models/bge-reranker-base.json‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
{
2+
"id": "145337e7-cec3-4ebb-8e78-16ddfc75e580",
3+
"source": 1,
4+
"name": "@cf/baai/bge-reranker-base",
5+
"description": "Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.\n\n",
6+
"task": {
7+
"id": "19606750-23ed-4371-aab2-c20349b53a60",
8+
"name": "Text Classification",
9+
"description": "Sentiment analysis or text classification is a common NLP task that classifies a text input into labels or classes."
10+
},
11+
"tags": [],
12+
"properties": [],
13+
"schema": {}
14+
}

‎src/content/workers-ai-models/llama-3.2-1b-instruct.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,7 @@
1212
"properties": [
1313
{
1414
"property_id": "context_window",
15-
"value": "128000"
15+
"value": "60000"
1616
},
1717
{
1818
"property_id": "terms",

‎src/content/workers-ai-models/llama-guard-3-8b.json‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -21,12 +21,14 @@
2121
"type": "object",
2222
"properties": {
2323
"role": {
24-
"type": "string",
25-
"description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."
24+
"enum": [
25+
"user",
26+
"assistant"
27+
],
28+
"description": "The role of the message sender must alternate between 'user' and 'assistant'."
2629
},
2730
"content": {
2831
"type": "string",
29-
"maxLength": 131072,
3032
"description": "The content of the message as a string."
3133
}
3234
},

‎src/content/workers-ai-models/whisper-large-v3-turbo.json‎

Lines changed: 51 additions & 53 deletions
Original file line numberDiff line numberDiff line change
@@ -9,12 +9,7 @@
99
"description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text."
1010
},
1111
"tags": [],
12-
"properties": [
13-
{
14-
"property_id": "beta",
15-
"value": "true"
16-
}
17-
],
12+
"properties": [],
1813
"schema": {
1914
"input": {
2015
"type": "object",
@@ -44,7 +39,7 @@
4439
},
4540
"prefix": {
4641
"type": "string",
47-
"description": "The prefix it appended the beginning of the output of the transcription and can guide the transcription result."
42+
"description": "The prefix it appended the the beginning of the output of the transcription and can guide the transcription result."
4843
}
4944
},
5045
"required": [
@@ -85,52 +80,55 @@
8580
"description": "The total number of words in the transcription."
8681
},
8782
"segments": {
88-
"type": "object",
89-
"properties": {
90-
"start": {
91-
"type": "number",
92-
"description": "The starting time of the segment within the audio, in seconds."
93-
},
94-
"end": {
95-
"type": "number",
96-
"description": "The ending time of the segment within the audio, in seconds."
97-
},
98-
"text": {
99-
"type": "string",
100-
"description": "The transcription of the segment."
101-
},
102-
"temperature": {
103-
"type": "number",
104-
"description": "The temperature used in the decoding process, controlling randomness in predictions. Lower values result in more deterministic outputs."
105-
},
106-
"avg_logprob": {
107-
"type": "number",
108-
"description": "The average log probability of the predictions for the words in this segment, indicating overall confidence."
109-
},
110-
"compression_ratio": {
111-
"type": "number",
112-
"description": "The compression ratio of the input to the output, measuring how much the text was compressed during the transcription process."
113-
},
114-
"no_speech_prob": {
115-
"type": "number",
116-
"description": "The probability that the segment contains no speech, represented as a decimal between 0 and 1."
117-
},
118-
"words": {
119-
"type": "array",
120-
"items": {
121-
"type": "object",
122-
"properties": {
123-
"word": {
124-
"type": "string",
125-
"description": "The individual word transcribed from the audio."
126-
},
127-
"start": {
128-
"type": "number",
129-
"description": "The starting time of the word within the audio, in seconds."
130-
},
131-
"end": {
132-
"type": "number",
133-
"description": "The ending time of the word within the audio, in seconds."
83+
"type": "array",
84+
"items": {
85+
"type": "object",
86+
"properties": {
87+
"start": {
88+
"type": "number",
89+
"description": "The starting time of the segment within the audio, in seconds."
90+
},
91+
"end": {
92+
"type": "number",
93+
"description": "The ending time of the segment within the audio, in seconds."
94+
},
95+
"text": {
96+
"type": "string",
97+
"description": "The transcription of the segment."
98+
},
99+
"temperature": {
100+
"type": "number",
101+
"description": "The temperature used in the decoding process, controlling randomness in predictions. Lower values result in more deterministic outputs."
102+
},
103+
"avg_logprob": {
104+
"type": "number",
105+
"description": "The average log probability of the predictions for the words in this segment, indicating overall confidence."
106+
},
107+
"compression_ratio": {
108+
"type": "number",
109+
"description": "The compression ratio of the input to the output, measuring how much the text was compressed during the transcription process."
110+
},
111+
"no_speech_prob": {
112+
"type": "number",
113+
"description": "The probability that the segment contains no speech, represented as a decimal between 0 and 1."
114+
},
115+
"words": {
116+
"type": "array",
117+
"items": {
118+
"type": "object",
119+
"properties": {
120+
"word": {
121+
"type": "string",
122+
"description": "The individual word transcribed from the audio."
123+
},
124+
"start": {
125+
"type": "number",
126+
"description": "The starting time of the word within the audio, in seconds."
127+
},
128+
"end": {
129+
"type": "number",
130+
"description": "The ending time of the word within the audio, in seconds."
131+
}
134132
}
135133
}
136134
}

0 commit comments

Comments
 (0)