Skip to content

[Workers AI] Model updates #25834

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: production
Choose a base branch
from
Open

[Workers AI] Model updates #25834

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions src/content/workers-ai-models/aura-1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,23 +15,23 @@
"property_id": "async_queue",
"value": "true"
},
{
"property_id": "partner",
"value": "true"
},
{
"property_id": "realtime",
"value": "true"
},
{
"property_id": "price",
"value": [
{
"unit": "per 1k characters",
"price": 0.0150,
"unit": "per audio minute",
"price": 0,
"currency": "USD"
}
]
},
{
"property_id": "partner",
"value": "true"
},
{
"property_id": "realtime",
"value": "true"
}
],
"schema": {
Expand Down
4 changes: 4 additions & 0 deletions src/content/workers-ai-models/bge-m3.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,10 @@
"property_id": "async_queue",
"value": "true"
},
{
"property_id": "context_window",
"value": "60000"
},
{
"property_id": "price",
"value": [
Expand Down
56 changes: 32 additions & 24 deletions src/content/workers-ai-models/embeddinggemma-300m.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
{
"id": "d2f07a41-c152-4061-8083-ec655cbf91a1",
"id": "15631501-2742-4346-a469-22fe202188a2",
"source": 1,
"name": "@cf/google/embeddinggemma-300m",
"description": "EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.",
Expand All @@ -8,51 +8,59 @@
"name": "Text Embeddings",
"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)."
},
"created_at": "2025-09-03 20:48:38.784",
"created_at": "2025-09-04 16:38:44.980",
"tags": [],
"properties": [],
"schema": {
"input": {
"type": "object",
"properties": {
"text": {
"oneOf": [{
"type": "string"
}, {
"type": "array",
"items": {
"type": "string"
"oneOf": [
{
"type": "string",
"description": "The text to embed",
"minLength": 1
},
{
"type": "array",
"description": "Batch of text values to embed",
"items": {
"type": "string",
"description": "The text to embed",
"minLength": 1
},
"maxItems": 100
}
}],
"description": "Input text to embed. Can be a single string or a list of strings."
]
}
},
"required": ["text"]
"required": [
"text"
]
},
"output": {
"type": "object",
"contentType": "application/json",
"properties": {
"shape": {
"type": "array",
"items": {
"type": "number"
}
},
"data": {
"type": "array",
"description": "Embeddings of the requested text values",
"items": {
"type": "array",
"description": "Floating point embedding representation shaped by the embedding model",
"items": {
"type": "number"
}
},
"description": "Embedding vectors, where each vector is a list of floats."
},
"shape": {
"type": "array",
"items": {
"type": "integer"
},
"minItems": 2,
"maxItems": 2,
"description": "Shape of the embedding data as [number_of_embeddings, embedding_dimension]."
}
}
},
"required": ["data", "shape"]
}
}
}
}
232 changes: 116 additions & 116 deletions src/content/workers-ai-models/flux.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,126 +21,126 @@
}
],
"schema": {
"input": {
"type": "object",
"properties": {
"encoding": {
"type": "string",
"description": "Encoding of the audio stream. Currently only supports raw signed little-endian 16-bit PCM.",
"enum": [
"linear16"
]
},
"sample_rate": {
"type": "string",
"description": "Sample rate of the audio stream in Hz.",
"pattern": "^[0-9]+$"
},
"eager_eot_threshold": {
"type": "string",
"description": "End-of-turn confidence required to fire an eager end-of-turn event. When set, enables EagerEndOfTurn and TurnResumed events. Valid Values 0.3 - 0.9."
},
"eot_threshold": {
"type": "string",
"description": "End-of-turn confidence required to finish a turn. Valid Values 0.5 - 0.9.",
"default": "0.7"
},
"eot_timeout_ms": {
"type": "string",
"description": "A turn will be finished when this much time has passed after speech, regardless of EOT confidence.",
"default": "5000",
"pattern": "^[0-9]+$"
},
"keyterm": {
"type": "string",
"description": "Keyterm prompting can improve recognition of specialized terminology. Pass multiple keyterm query parameters to boost multiple keyterms."
},
"mip_opt_out": {
"type": "string",
"description": "Opts out requests from the Deepgram Model Improvement Program. Refer to Deepgram Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip",
"enum": [
"true",
"false"
],
"default": "false"
},
"tag": {
"type": "string",
"description": "Label your requests for the purpose of identification during usage reporting"
},
"required": [
"sample_rate",
"encoding"
]
}
},
"output": {
"type": "object",
"description": "Output will be returned as websocket messages.",
"properties": {
"request_id": {
"type": "string",
"description": "The unique identifier of the request (uuid)"
},
"sequence_id": {
"type": "integer",
"description": "Starts at 0 and increments for each message the server sends to the client.",
"minimum": 0
},
"event": {
"type": "string",
"description": "The type of event being reported.",
"enum": [
"Update",
"StartOfTurn",
"EagerEndOfTurn",
"TurnResumed",
"EndOfTurn"
"input": {
"type": "object",
"properties": {
"encoding": {
"type": "string",
"description": "Encoding of the audio stream. Currently only supports raw signed little-endian 16-bit PCM.",
"enum": [
"linear16"
]
},
"sample_rate": {
"type": "string",
"description": "Sample rate of the audio stream in Hz.",
"pattern": "^[0-9]+$"
},
"eager_eot_threshold": {
"type": "string",
"description": "End-of-turn confidence required to fire an eager end-of-turn event. When set, enables EagerEndOfTurn and TurnResumed events. Valid Values 0.3 - 0.9."
},
"eot_threshold": {
"type": "string",
"description": "End-of-turn confidence required to finish a turn. Valid Values 0.5 - 0.9.",
"default": "0.7"
},
"eot_timeout_ms": {
"type": "string",
"description": "A turn will be finished when this much time has passed after speech, regardless of EOT confidence.",
"default": "5000",
"pattern": "^[0-9]+$"
},
"keyterm": {
"type": "string",
"description": "Keyterm prompting can improve recognition of specialized terminology. Pass multiple keyterm query parameters to boost multiple keyterms."
},
"mip_opt_out": {
"type": "string",
"description": "Opts out requests from the Deepgram Model Improvement Program. Refer to Deepgram Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip",
"enum": [
"true",
"false"
],
"default": "false"
},
"tag": {
"type": "string",
"description": "Label your requests for the purpose of identification during usage reporting"
}
},
"required": [
"sample_rate",
"encoding"
]
},
"turn_index": {
"type": "integer",
"description": "The index of the current turn",
"minimum": 0
},
"audio_window_start": {
"type": "number",
"description": "Start time in seconds of the audio range that was transcribed"
},
"audio_window_end": {
"type": "number",
"description": "End time in seconds of the audio range that was transcribed"
},
"transcript": {
"type": "string",
"description": "Text that was said over the course of the current turn"
},
"words": {
"type": "array",
"description": "The words in the transcript",
"items": {
"type": "object",
"required": [
"word",
"confidence"
],
"properties": {
"word": {
"type": "string",
"description": "The individual punctuated, properly-cased word from the transcript"
},
"output": {
"type": "object",
"description": "Output will be returned as websocket messages.",
"properties": {
"request_id": {
"type": "string",
"description": "The unique identifier of the request (uuid)"
},
"sequence_id": {
"type": "integer",
"description": "Starts at 0 and increments for each message the server sends to the client.",
"minimum": 0
},
"event": {
"type": "string",
"description": "The type of event being reported.",
"enum": [
"Update",
"StartOfTurn",
"EagerEndOfTurn",
"TurnResumed",
"EndOfTurn"
]
},
"turn_index": {
"type": "integer",
"description": "The index of the current turn",
"minimum": 0
},
"audio_window_start": {
"type": "number",
"description": "Start time in seconds of the audio range that was transcribed"
},
"audio_window_end": {
"type": "number",
"description": "End time in seconds of the audio range that was transcribed"
},
"transcript": {
"type": "string",
"description": "Text that was said over the course of the current turn"
},
"words": {
"type": "array",
"description": "The words in the transcript",
"items": {
"type": "object",
"required": [
"word",
"confidence"
],
"properties": {
"word": {
"type": "string",
"description": "The individual punctuated, properly-cased word from the transcript"
},
"confidence": {
"type": "number",
"description": "Confidence that this word was transcribed correctly"
}
}
}
},
"confidence": {
"type": "number",
"description": "Confidence that this word was transcribed correctly"
"end_of_turn_confidence": {
"type": "number",
"description": "Confidence that no more speech is coming in this turn"
}
}
}
},
"end_of_turn_confidence": {
"type": "number",
"description": "Confidence that no more speech is coming in this turn"
}
}
}
}
}
Loading