Cloudflare/workers Ai

@webframp/cloudflare/workers-aiv2026.07.19.1· 6d agoMODELS

01README

Cloudflare Workers AI — model inference, fine-tuning, LoRA adapters

02Release Notes

2026.07.19.1

Added: Initial code-generated release of @webframp/cloudflare/workers-ai with 228 methods covering the Cloudflare workers ai API surface.

03Models1

cloudflare/workers_ai.tsv2026.07.19.1

Global Arguments

Argument	Type	Required	Description
apiToken	string	yes	Cloudflare API token
accountId	string	yes	Cloudflare account ID

fn get_credit_balance()

Get credit balance

fn get_invoice_history(type?: enum)

Get invoice history

Argument	Type	Required	Description
type?	enum	no	Filter invoice type: auto, manual, or all.

fn get_invoice_preview()

Get invoice preview

fn get_spending_limit()

Get spending limit

fn delete_spending_limit()

Delete spending limit

fn create_topup(amount: number)

Create a top-up

Argument	Type	Required	Description
amount	number	yes	Top-up amount in cents (min 1000).

fn get_topup_config()

Get auto top-up configuration

fn create_aig_billing_set_topup_config(amount: number, threshold: number)

Set auto top-up configuration

Argument	Type	Required	Description
amount	number	yes	Auto top-up amount in cents (min 1000).
threshold	number	yes	Balance threshold in cents that triggers auto top-up (min 500).

fn delete_topup_config()

Delete auto top-up configuration

fn get_topup_limits()

Get account top-up limits

fn create_aig_billing_check_topup_status(payment_intent_id: string)

Check top-up status

Argument	Type	Required	Description
payment_intent_id	string	yes	Stripe invoice ID to check status for.

fn get_usage_history(value_grouping_window?: enum, start_time?: number, end_time?: number)

Get usage history

Argument	Type	Required	Description
value_grouping_window?	enum	no	Grouping window for usage data.
start_time?	number	no	Start time as Unix timestamp in milliseconds.
end_time?	number	no	End time as Unix timestamp in milliseconds.

fn list_account_provider(page?: number, per_page?: number, beta?: boolean, enable?: boolean, search?: string)

List Account Providers

Argument	Type	Required
page?	number	no
per_page?	number	no
beta?	boolean	no
enable?	boolean	no
search?	string	no

fn create_account_provider(base_url: string, beta?: boolean, curl_example?: string, description?: string, enable?: boolean, headers?: string, js_example?: string, link?: string, name: string, position?: number, slug: string)

Create a new Account Provider

Argument	Type	Required
base_url	string	yes
beta?	boolean	no
curl_example?	string	no
description?	string	no
enable?	boolean	no
headers?	string	no
js_example?	string	no
link?	string	no
name	string	yes
position?	number	no
slug	string	yes

fn list_account_provider_cost(page?: number, per_page?: number, enable?: boolean, account_provider_id?: string, model_rule?: enum, cost_type?: string, search?: string)

List Account Provider Costs

Argument	Type	Required
page?	number	no
per_page?	number	no
enable?	boolean	no
account_provider_id?	string	no
model_rule?	enum	no
cost_type?	string	no
search?	string	no

fn create_account_provider_cost(account_provider_id: string, cost_in?: number, cost_out?: number, cost_type?: string, enable?: boolean, model: string, model_rule?: enum, token_pricing?: object)

Create a new Account Provider Cost

Argument	Type	Required
account_provider_id	string	yes
cost_in?	number	no
cost_out?	number	no
cost_type?	string	no
enable?	boolean	no
model	string	yes
model_rule?	enum	no
token_pricing?	object	no

fn get_aig_config_fetch_account_provider_cost(id: string)

Fetch a Account Provider Cost

Argument	Type	Required	Description
id	string	yes

fn update_account_provider_cost(id: string, cost_in?: number, cost_out?: number, cost_type?: string, enable?: boolean, model?: string, model_rule?: enum, token_pricing?: object)

Update a Account Provider Cost

Argument	Type	Required
id	string	yes
cost_in?	number	no
cost_out?	number	no
cost_type?	string	no
enable?	boolean	no
model?	string	no
model_rule?	enum	no
token_pricing?	object	no

fn delete_account_provider_cost(id: string)

Delete a Account Provider Cost

Argument	Type	Required	Description
id	string	yes

fn get_aig_config_fetch_account_provider(id: string)

Fetch a Account Provider

Argument	Type	Required	Description
id	string	yes

fn update_account_provider(id: string, base_url?: string, beta?: boolean, curl_example?: string, description?: string, enable?: boolean, headers?: string, js_example?: string, link?: string, logo?: string, name?: string, position?: number, slug?: string)

Update a Account Provider

Argument	Type	Required
id	string	yes
base_url?	string	no
beta?	boolean	no
curl_example?	string	no
description?	string	no
enable?	boolean	no
headers?	string	no
js_example?	string	no
link?	string	no
logo?	string	no
name?	string	no
position?	number	no
slug?	string	no

fn delete_account_provider(id: string)

Delete a Account Provider

Argument	Type	Required	Description
id	string	yes

fn list_evaluators(page?: number, per_page?: number, order_by?: string, order_by_direction?: enum)

List Evaluators

Argument	Type	Required
page?	number	no
per_page?	number	no
order_by?	string	no
order_by_direction?	enum	no

fn list_gateway(page?: number, per_page?: number, search?: string)

List Gateways

Argument	Type	Required
page?	number	no
per_page?	number	no
search?	string	no

fn create_gateway(authentication?: boolean, cache_invalidate_on_update: boolean, cache_ttl: number, collect_logs: boolean, log_management?: number, log_management_strategy?: enum, logpush?: boolean, logpush_public_key?: string, rate_limiting_interval: number, rate_limiting_limit: number, rate_limiting_technique?: enum, retry_backoff?: enum, retry_delay?: number, retry_max_attempts?: number, workers_ai_billing_mode?: enum, zdr?: boolean)

Create a new Gateway

Argument	Type	Required	Description
authentication?	boolean	no
cache_invalidate_on_update	boolean	yes
cache_ttl	number	yes
collect_logs	boolean	yes
log_management?	number	no
log_management_strategy?	enum	no
logpush?	boolean	no
logpush_public_key?	string	no
rate_limiting_interval	number	yes
rate_limiting_limit	number	yes
rate_limiting_technique?	enum	no
retry_backoff?	enum	no	Backoff strategy for retry delays
retry_delay?	number	no	Delay between retry attempts in milliseconds (0-5000)
retry_max_attempts?	number	no	Maximum number of retry attempts for failed requests (1-5)
workers_ai_billing_mode?	enum	no	Controls how Workers AI inference calls routed through this gateway are bille...
zdr?	boolean	no

fn list_dataset(gateway_id: string, page?: number, per_page?: number, name?: string, enable?: boolean, search?: string)

List Datasets

Argument	Type	Required
gateway_id	string	yes
page?	number	no
per_page?	number	no
name?	string	no
enable?	boolean	no
search?	string	no

fn create_dataset(gateway_id: string, enable: boolean, filters: array, name: string)

Create a new Dataset

Argument	Type	Required
gateway_id	string	yes
enable	boolean	yes
filters	array	yes
name	string	yes

fn get_aig_config_fetch_dataset(gateway_id: string, id: string)

Fetch a Dataset

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn update_dataset(gateway_id: string, id: string, enable: boolean, filters: array, name: string)

Update a Dataset

Argument	Type	Required
gateway_id	string	yes
id	string	yes
enable	boolean	yes
filters	array	yes
name	string	yes

fn delete_dataset(gateway_id: string, id: string)

Delete a Dataset

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn list_evaluations(gateway_id: string, page?: number, per_page?: number, name?: string, processed?: boolean, search?: string)

List Evaluations

Argument	Type	Required
gateway_id	string	yes
page?	number	no
per_page?	number	no
name?	string	no
processed?	boolean	no
search?	string	no

fn create_evaluations(gateway_id: string, dataset_ids: array, evaluation_type_ids: array, name: string)

Create a new Evaluation

Argument	Type	Required
gateway_id	string	yes
dataset_ids	array	yes
evaluation_type_ids	array	yes
name	string	yes

fn get_aig_config_fetch_evaluations(gateway_id: string, id: string)

Fetch a Evaluation

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn delete_evaluations(gateway_id: string, id: string)

Delete a Evaluation

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn list_gateway_logs(gateway_id: string, search?: string, page?: number, per_page?: number, order_by?: enum, order_by_direction?: enum, filters?: string, meta_info?: boolean, direction?: enum, start_date?: string, end_date?: string, min_cost?: number, max_cost?: number, min_tokens_in?: number, max_tokens_in?: number, min_tokens_out?: number, max_tokens_out?: number, min_total_tokens?: number, max_total_tokens?: number, min_duration?: number, max_duration?: number, feedback?: string, success?: boolean, cached?: boolean, model?: string, model_type?: string, provider?: string, request_content_type?: string, response_content_type?: string)

List Gateway Logs

Argument	Type	Required
gateway_id	string	yes
search?	string	no
page?	number	no
per_page?	number	no
order_by?	enum	no
order_by_direction?	enum	no
filters?	string	no
meta_info?	boolean	no
direction?	enum	no
start_date?	string	no
end_date?	string	no
min_cost?	number	no
max_cost?	number	no
min_tokens_in?	number	no
max_tokens_in?	number	no
min_tokens_out?	number	no
max_tokens_out?	number	no
min_total_tokens?	number	no
max_total_tokens?	number	no
min_duration?	number	no
max_duration?	number	no
feedback?	string	no
success?	boolean	no
cached?	boolean	no
model?	string	no
model_type?	string	no
provider?	string	no
request_content_type?	string	no
response_content_type?	string	no

fn delete_gateway_logs(gateway_id: string, order_by?: enum, order_by_direction?: enum, filters?: string, limit?: number)

Delete Gateway Logs

Argument	Type	Required
gateway_id	string	yes
order_by?	enum	no
order_by_direction?	enum	no
filters?	string	no
limit?	number	no

fn get_gateway_log_detail(id: string, gateway_id: string)

Get Gateway Log Detail

Argument	Type	Required	Description
id	string	yes
gateway_id	string	yes

fn patch_gateway_log(id: string, gateway_id: string, feedback?: number, metadata?: record, score?: number)

Patch Gateway Log

Argument	Type	Required
id	string	yes
gateway_id	string	yes
feedback?	number	no
metadata?	record	no
score?	number	no

fn get_gateway_log_request(id: string, gateway_id: string)

Get Gateway Log Request

Argument	Type	Required	Description
id	string	yes
gateway_id	string	yes

fn get_gateway_log_response(id: string, gateway_id: string)

Get Gateway Log Response

Argument	Type	Required	Description
id	string	yes
gateway_id	string	yes

fn list_providers(gateway_id: string, page?: number, per_page?: number)

List Provider Configs

Argument	Type	Required
gateway_id	string	yes
page?	number	no
per_page?	number	no

fn create_providers(gateway_id: string, alias: string, default_config: boolean, provider_slug: string, rate_limit?: number, rate_limit_period?: number, secret?: string, secret_id?: string)

Create a new Provider Configs

Argument	Type	Required
gateway_id	string	yes
alias	string	yes
default_config	boolean	yes
provider_slug	string	yes
rate_limit?	number	no
rate_limit_period?	number	no
secret?	string	no
secret_id?	string	no

fn update_providers(gateway_id: string, id: string, secret: string)

Update a Provider Configs

Argument	Type	Required
gateway_id	string	yes
id	string	yes
secret	string	yes

fn delete_providers(gateway_id: string, id: string)

Delete a Provider Configs

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn list_gateway_dynamic_routes(gateway_id: string, page?: number, per_page?: number)

List all AI Gateway Dynamic Routes.

Argument	Type	Required	Description
gateway_id	string	yes
page?	number	no	Page number
per_page?	number	no	Number of routes per page

fn create_aig_config_post_gateway_dynamic_route(gateway_id: string, elements?: array, name: string)

Create a new AI Gateway Dynamic Route.

Argument	Type	Required
gateway_id	string	yes
elements?	array	no
name	string	yes

fn get_gateway_dynamic_route(gateway_id: string, id: string)

Get an AI Gateway Dynamic Route.

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn update_gateway_dynamic_route(gateway_id: string, id: string, name: string)

Update an AI Gateway Dynamic Route.

Argument	Type	Required
gateway_id	string	yes
id	string	yes
name	string	yes

fn delete_gateway_dynamic_route(gateway_id: string, id: string)

Delete an AI Gateway Dynamic Route.

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn list_gateway_dynamic_route_deployments(gateway_id: string, id: string)

List all AI Gateway Dynamic Route Deployments.

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn create_aig_config_post_gateway_dynamic_route_deployment(gateway_id: string, id: string, version_id: string)

Create a new AI Gateway Dynamic Route Deployment.

Argument	Type	Required
gateway_id	string	yes
id	string	yes
version_id	string	yes

fn list_gateway_dynamic_route_versions(gateway_id: string, id: string)

List all AI Gateway Dynamic Route Versions.

Argument	Type	Required	Description
gateway_id	string	yes
id	string	yes

fn create_aig_config_post_gateway_dynamic_route_version(gateway_id: string, id: string, elements?: array)

Create a new AI Gateway Dynamic Route Version.

Argument	Type	Required
gateway_id	string	yes
id	string	yes
elements?	array	no

fn get_gateway_dynamic_route_version(gateway_id: string, id: string, version_id: string)

Get an AI Gateway Dynamic Route Version.

Argument	Type	Required
gateway_id	string	yes
id	string	yes
version_id	string	yes

fn get_gateway_url(gateway_id: string, provider: string)

Get Gateway URL

Argument	Type	Required	Description
gateway_id	string	yes
provider	string	yes

fn get_aig_config_fetch_gateway(id: string)

Fetch a Gateway

Argument	Type	Required	Description
id	string	yes

fn update_gateway(id: string, authentication?: boolean, cache_invalidate_on_update: boolean, cache_ttl: number, collect_logs: boolean, dlp?: union, guardrails?: object, log_management?: number, log_management_strategy?: enum, logpush?: boolean, logpush_public_key?: string, otel?: array, rate_limiting_interval: number, rate_limiting_limit: number, rate_limiting_technique?: enum, retry_backoff?: enum, retry_delay?: number, retry_max_attempts?: number, spend_limits?: object, store_id?: string, stripe?: object, workers_ai_billing_mode?: enum, zdr?: boolean)

Update a Gateway

Argument	Type	Required	Description
id	string	yes
authentication?	boolean	no
cache_invalidate_on_update	boolean	yes
cache_ttl	number	yes
collect_logs	boolean	yes
dlp?	union	no
guardrails?	object	no
log_management?	number	no
log_management_strategy?	enum	no
logpush?	boolean	no
logpush_public_key?	string	no
otel?	array	no
rate_limiting_interval	number	yes
rate_limiting_limit	number	yes
rate_limiting_technique?	enum	no
retry_backoff?	enum	no	Backoff strategy for retry delays
retry_delay?	number	no	Delay between retry attempts in milliseconds (0-5000)
retry_max_attempts?	number	no	Maximum number of retry attempts for failed requests (1-5)
spend_limits?	object	no
store_id?	string	no
stripe?	object	no
workers_ai_billing_mode?	enum	no	Controls how Workers AI inference calls routed through this gateway are bille...
zdr?	boolean	no

fn delete_gateway(id: string)

Delete a Gateway

Argument	Type	Required	Description
id	string	yes

fn list_instances(page?: number, per_page?: number, search?: string, namespace?: string, order_by?: enum, order_by_direction?: enum)

List AI Search instances.

Argument	Type	Required	Description
page?	number	no	Page number (1-indexed).
per_page?	number	no	Number of results per page.
search?	string	no	Filter instances whose id contains this string (case-insensitive).
namespace?	string	no	Filter by namespace.
order_by?	enum	no	Field to order results by.
order_by_direction?	enum	no	Order direction.

fn create_instance(ai_gateway_id?: string, ai_search_model?: union, cache?: boolean, cache_threshold?: enum, cache_ttl?: union, chunk?: boolean, chunk_overlap?: number, chunk_size?: number, custom_metadata?: array, embedding_model?: union, fusion_method?: enum, hybrid_search_enabled?: boolean, index_method?: object, indexing_options?: object, max_num_results?: number, metadata?: object, public_endpoint_params?: object, reranking?: boolean, reranking_model?: union, retrieval_options?: object, rewrite_model?: union, rewrite_query?: boolean, score_threshold?: number, source?: string, source_params?: object, sync_interval?: union, token_id?: string, type?: union)

Create an AI Search instance.

Argument	Type	Required	Description
ai_gateway_id?	string	no
ai_search_model?	union	no
cache?	boolean	no
cache_threshold?	enum	no
cache_ttl?	union	no	Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (...
chunk?	boolean	no
chunk_overlap?	number	no
chunk_size?	number	no
custom_metadata?	array	no
embedding_model?	union	no
fusion_method?	enum	no
hybrid_search_enabled?	boolean	no	Deprecated — use index_method instead.
index_method?	object	no	Controls which storage backends are used during indexing. Defaults to vector-...
indexing_options?	object	no
max_num_results?	number	no
metadata?	object	no
public_endpoint_params?	object	no
reranking?	boolean	no
reranking_model?	union	no
retrieval_options?	object	no
rewrite_model?	union	no
rewrite_query?	boolean	no
score_threshold?	number	no
source?	string	no
source_params?	object	no
sync_interval?	union	no	Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 18...
token_id?	string	no
type?	union	no

fn get_ai_search_fetch_instance(id: string)

Get an AI Search instance.

Argument	Type	Required	Description
id	string	yes

fn update_instance(id: string, ai_gateway_id?: string, ai_search_model?: union, cache?: boolean, cache_threshold?: enum, cache_ttl?: union, chunk?: boolean, chunk_overlap?: number, chunk_size?: number, custom_metadata?: array, embedding_model?: union, fusion_method?: enum, index_method?: object, indexing_options?: object, max_num_results?: number, metadata?: object, paused?: boolean, public_endpoint_params?: object, reranking?: boolean, reranking_model?: union, retrieval_options?: object, rewrite_model?: union, rewrite_query?: boolean, score_threshold?: number, source?: string, source_params?: object, summarization?: boolean, summarization_model?: union, sync_interval?: union, system_prompt_ai_search?: string, system_prompt_index_summarization?: string, system_prompt_rewrite_query?: string, token_id?: string)

Update an AI Search instance.

Argument	Type	Required	Description
id	string	yes
ai_gateway_id?	string	no
ai_search_model?	union	no
cache?	boolean	no
cache_threshold?	enum	no
cache_ttl?	union	no	Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (...
chunk?	boolean	no
chunk_overlap?	number	no
chunk_size?	number	no
custom_metadata?	array	no
embedding_model?	union	no
fusion_method?	enum	no
index_method?	object	no	Controls which storage backends are used during indexing. Defaults to vector-...
indexing_options?	object	no
max_num_results?	number	no
metadata?	object	no
paused?	boolean	no
public_endpoint_params?	object	no
reranking?	boolean	no
reranking_model?	union	no
retrieval_options?	object	no
rewrite_model?	union	no
rewrite_query?	boolean	no
score_threshold?	number	no
source?	string	no
source_params?	object	no
summarization?	boolean	no
summarization_model?	union	no
sync_interval?	union	no	Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 18...
system_prompt_ai_search?	string	no
system_prompt_index_summarization?	string	no
system_prompt_rewrite_query?	string	no
token_id?	string	no

fn delete_instance(id: string)

Delete an AI Search instance.

Argument	Type	Required	Description
id	string	yes

fn create_ai_search_instance_chat_completion(id: string, ai_search_options?: object, messages: array, model?: union, stream?: boolean)

Chat Completions

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
ai_search_options?	object	no
messages	array	yes
model?	union	no
stream?	boolean	no

fn list_jobs(id: string, page?: number, per_page?: number)

List Jobs

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
page?	number	no
per_page?	number	no

fn create_job(id: string, description?: string)

Create new job

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
description?	string	no

fn get_job(id: string, job_id: string)

Get a Job Details

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
job_id	string	yes

fn update_ai_search_instance_change_job_status(id: string, job_id: string, action: enum)

Cancel an indexing job.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
job_id	string	yes
action	enum	yes

fn list_job_logs(id: string, job_id: string, page?: number, per_page?: number)

List Job Logs

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
job_id	string	yes
page?	number	no
per_page?	number	no

fn create_ai_search_instance_search(id: string, ai_search_options?: object, messages?: array, query?: string)

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
ai_search_options?	object	no
messages?	array	no	OpenAI-compatible message array. For multimodal queries, set the last user me...
query?	string	no	A simple text query string. Alternative to 'messages' — provide either this o...

fn get_ai_search_stats(id: string)

Get instance statistics.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.

fn list_namespaces(page?: number, per_page?: number, search?: string)

List namespaces.

Argument	Type	Required	Description
page?	number	no	Page number (1-indexed).
per_page?	number	no	Number of results per page.
search?	string	no	Filter namespaces whose name or description contains this string (case-insensitive).

fn create_namespace(description?: string, name: string)

Create namespace.

Argument	Type	Required	Description
description?	string	no	Optional description for the namespace. Max 256 characters.
name	string	yes

fn get_ai_search_fetch_namespace(name: string)

Read namespace.

Argument	Type	Required	Description
name	string	yes

fn update_namespace(name: string, description?: string)

Update namespace.

Argument	Type	Required	Description
name	string	yes
description?	string	no	Optional description for the namespace. Max 256 characters.

fn delete_namespace(name: string)

Delete namespace.

Argument	Type	Required	Description
name	string	yes

fn create_ai_search_namespace_multi_instance_chat_completion(name: string, ai_search_options?: object, messages: array, model?: union, stream?: boolean)

Multi-Instance Chat Completions

Argument	Type	Required	Description
name	string	yes	Namespace name
ai_search_options?	object	no
messages	array	yes
model?	union	no
stream?	boolean	no

fn get_ai_search_namespace_fetch_instance(id: string, name: string)

Get an AI Search instance.

Argument	Type	Required	Description
id	string	yes
name	string	yes	Namespace name

fn update_ai_search_move_instance(name: string, id: string, new_namespace: string)

Move an instance to a different namespace.

Argument	Type	Required	Description
name	string	yes	Current namespace of the instance.
id	string	yes	Instance id.
new_namespace	string	yes	Target namespace to move the instance into.

fn create_ai_search_namespace_instance_chat_completion(id: string, name: string, ai_search_options?: object, messages: array, model?: union, stream?: boolean)

Chat Completions

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name
ai_search_options?	object	no
messages	array	yes
model?	union	no
stream?	boolean	no

fn list_items(id: string, name: string, page?: number, per_page?: number, search?: string, sort_by?: enum, status?: enum, source?: string, metadata_filter?: string, item_id?: string, key?: string)

Items List.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name
page?	number	no
per_page?	number	no
search?	string	no
sort_by?	enum	no	Sort order for items. "status" (default) sorts by status priority then last_seen_at. "modified_at" sorts by file modification time (most recent first), falling back to created_at.
status?	enum	no
source?	string	no	Filter items by source_id. Use "builtin" for uploaded files, or a source identifier like "web-crawler:https://example.com".
metadata_filter?	string	no	JSON-encoded metadata filter using Vectorize filter syntax. Examples: {"folder":"reports/"}, {"timestamp":{"$gte":1700000000000}}, {"folder":{"$in":["docs/","reports/"]}}
item_id?	string	no	Filter items by their unique ID. Returns at most one item.
key?	string	no	Filter items by their exact key (object key / filename). Keys are unique per source, so combine with `source` to disambiguate across data sources.

fn ai_search_namespace_instance_upload_item(id: string, name: string)

Upload Item.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name

fn create_or_update_item(id: string, name: string, key: string, next_action: enum, wait_for_completion?: boolean)

Create or Update Item.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name
key	string	yes	Item key / filename. Must not exceed 128 characters.
next_action	enum	yes
wait_for_completion?	boolean	no	Wait for indexing to fully complete before responding. On RAGs with vector in...

fn get_item(id: string, item_id: string, name: string)

Get Item.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
item_id	string	yes
name	string	yes	Namespace name

fn update_ai_search_namespace_instance_sync_item(id: string, item_id: string, name: string, next_action: enum, wait_for_completion?: boolean)

Sync Item.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
item_id	string	yes
name	string	yes	Namespace name
next_action	enum	yes
wait_for_completion?	boolean	no	Wait for indexing to fully complete before responding. On RAGs with vector in...

fn delete_item(id: string, item_id: string, name: string)

Delete Item.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
item_id	string	yes
name	string	yes	Namespace name

fn list_item_chunks(id: string, item_id: string, name: string, limit?: number, offset?: number)

List Item Chunks.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
item_id	string	yes
name	string	yes	Namespace name
limit?	number	no
offset?	number	no

fn list_ai_search_namespace_instance_logs_item(id: string, item_id: string, name: string, limit?: number, cursor?: string)

Item Logs.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
item_id	string	yes
name	string	yes	Namespace name
limit?	number	no
cursor?	string	no

fn update_ai_search_namespace_instance_change_job_status(id: string, job_id: string, name: string, action: enum)

Cancel an indexing job.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
job_id	string	yes
name	string	yes	Namespace name
action	enum	yes

fn create_ai_search_namespace_instance_search(id: string, name: string, ai_search_options?: object, messages?: array, query?: string)

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name
ai_search_options?	object	no
messages?	array	no	OpenAI-compatible message array. For multimodal queries, set the last user me...
query?	string	no	A simple text query string. Alternative to 'messages' — provide either this o...

fn get_ai_search_namespace_stats(id: string, name: string)

Get instance statistics.

Argument	Type	Required	Description
id	string	yes	AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
name	string	yes	Namespace name

fn create_ai_search_namespace_multi_instance_search(name: string, ai_search_options?: object, messages?: array, query?: string)

Multi-Instance Search

Argument	Type	Required	Description
name	string	yes	Namespace name
ai_search_options?	object	no
messages?	array	no	OpenAI-compatible message array. For multimodal queries, set the last user me...
query?	string	no	A simple text query string. Alternative to 'messages' — provide either this o...

fn list_tokens(page?: number, per_page?: number, search?: string)

List tokens.

Argument	Type	Required	Description
page?	number	no	Page number (1-indexed).
per_page?	number	no	Number of results per page.
search?	string	no	Filter tokens whose name contains this string (case-insensitive).

fn create_tokens(cf_api_id: string, cf_api_key: string, legacy?: boolean, name: string)

Create token.

Argument	Type	Required
cf_api_id	string	yes
cf_api_key	string	yes
legacy?	boolean	no
name	string	yes

fn get_ai_search_fetch_tokens(id: string)

Read token.

Argument	Type	Required	Description
id	string	yes

fn update_tokens(id: string, cf_api_id: string, cf_api_key: string, legacy?: boolean, name: string)

Update token.

Argument	Type	Required
id	string	yes
cf_api_id	string	yes
cf_api_key	string	yes
legacy?	boolean	no
name	string	yes

fn delete_tokens(id: string)

Delete token.

Argument	Type	Required	Description
id	string	yes

fn list_workers_ai_search_author()

Author Search

fn list_finetunes()

List Finetunes

fn create_finetune(description?: string, model: string, name: string, public?: boolean)

Create a new Finetune

Argument	Type	Required
description?	string	no
model	string	yes
name	string	yes
public?	boolean	no

fn list_public_finetunes(limit?: number, offset?: number, orderBy?: string)

List Public Finetunes

Argument	Type	Required	Description
limit?	number	no	Pagination Limit
offset?	number	no	Pagination Offset
orderBy?	string	no	Order By Column Name

fn workers_ai_upload_finetune_asset(finetune_id: string)

Upload a Finetune Asset

Argument	Type	Required	Description
finetune_id	string	yes

fn get_model_schema(model?: string)

Get Model Schema

Argument	Type	Required	Description
model?	string	no	Model Name

fn get_workers_ai_search_model(per_page?: number, page?: number, task?: string, author?: string, source?: number, hide_experimental?: boolean, search?: string, include_deprecated?: boolean, format?: enum)

Model Search

Argument	Type	Required	Description
per_page?	number	no
page?	number	no
task?	string	no	Filter by Task Name
author?	string	no	Filter by Author
source?	number	no	Filter by Source Id
hide_experimental?	boolean	no	Filter to hide experimental models
search?	string	no	Search
include_deprecated?	boolean	no	If true, include models whose planned_deprecation_date is in the past — but only within a three-month grace window after that date. Models whose planned_deprecation_date is more than three months in the past remain hidden regardless of this flag. Future planned-deprecation dates are always included regardless of this flag. Defaults to false, preserving the existing behavior of hiding all past-dated deprecations.
format?	enum	no	If set, return models in the requested marketplace format instead of the default response.

fn create_workers_ai_post_run_generic(input: object, model: string, options?: object)

Execute AI Model (Generic)

Argument	Type	Required	Description
input	object	yes	Model-specific input data. Format varies by model type.
model	string	yes	The AI model to execute (e.g., openai/gpt-5.5, anthropic/claude-opus-4.7)
options?	object	no

fn create_workers_ai_post_run_cf_ai4bharat_indictrans2_en_indic_1b(queueRequest?: string, tags?: string, target_language: enum, text: union)

Execute @cf/ai4bharat/indictrans2-en-indic-1B model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
target_language	enum	yes	Target langauge to translate to
text	union	yes	Input text to translate. Can be a single string or a list of strings.

fn create_workers_ai_post_run_cf_ai4bharat_nonomni_indictrans2_en_indic_1b(queueRequest?: string, tags?: string, target_language: enum, text: union)

Execute @cf/ai4bharat/nonomni-indictrans2-en-indic-1b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
target_language	enum	yes	Target langauge to translate to
text	union	yes	Input text to translate. Can be a single string or a list of strings.

fn workers_ai_post_run_cf_aisingapore_gemma_sea_lion_v4_27b_it(queueRequest?: string, tags?: string)

Execute @cf/aisingapore/gemma-sea-lion-v4-27b-it model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_bge_base_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/bge-base-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_bge_large_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/bge-large-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_bge_m3(queueRequest?: string, tags?: string)

Execute @cf/baai/bge-m3 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_baai_bge_reranker_base(queueRequest?: string, tags?: string, contexts?: array, query: string, top_k?: number)

Execute @cf/baai/bge-reranker-base model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
contexts?	array	no	List of provided contexts. Note that the index in this array is important, as...
query	string	yes	A query you wish to perform against the provided contexts.
top_k?	number	no	Number of returned results starting with the best score.

fn workers_ai_post_run_cf_baai_bge_small_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/bge-small-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_nonomni_bge_base_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/nonomni-bge-base-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_nonomni_bge_large_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/nonomni-bge-large-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_nonomni_bge_m3(queueRequest?: string, tags?: string)

Execute @cf/baai/nonomni-bge-m3 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_baai_nonomni_bge_small_en_v1_5(queueRequest?: string, tags?: string)

Execute @cf/baai/nonomni-bge-small-en-v1.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_black_forest_labs_flux_1_schnell(queueRequest?: string, tags?: string, prompt: string, steps?: number)

Execute @cf/black-forest-labs/flux-1-schnell model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
prompt	string	yes	A text description of the image you want to generate.
steps?	number	no	The number of diffusion steps; higher values can improve quality but take lon...

fn create_workers_ai_post_run_cf_black_forest_labs_flux_2_dev(queueRequest?: string, tags?: string, multipart?: object)

Execute @cf/black-forest-labs/flux-2-dev model.

Argument	Type	Required
queueRequest?	string	no
tags?	string	no
multipart?	object	no

fn create_workers_ai_post_run_cf_black_forest_labs_flux_2_klein_4b(queueRequest?: string, tags?: string, multipart?: object)

Execute @cf/black-forest-labs/flux-2-klein-4b model.

Argument	Type	Required
queueRequest?	string	no
tags?	string	no
multipart?	object	no

fn create_workers_ai_post_run_cf_black_forest_labs_flux_2_klein_9b(queueRequest?: string, tags?: string, multipart?: object)

Execute @cf/black-forest-labs/flux-2-klein-9b model.

Argument	Type	Required
queueRequest?	string	no
tags?	string	no
multipart?	object	no

fn create_workers_ai_post_run_cf_bytedance_stable_diffusion_xl_lightning(queueRequest?: string, tags?: string, guidance?: number, height?: number, image?: array, image_b64?: string, mask?: array, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, strength?: number, width?: number)

Execute @cf/bytedance/stable-diffusion-xl-lightning model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
image?	array	no	For use with img2img tasks. An array of integers that represent the image dat...
image_b64?	string	no	For use with img2img tasks. A base64-encoded string of the input image
mask?	array	no	An array representing An array of integers that represent mask image data for...
negative_prompt?	string	no	Text describing elements to avoid in the generated image
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate
seed?	number	no	Random seed for reproducibility of the image generation
strength?	number	no	A value between 0 and 1 indicating how strongly to apply the transformation d...
width?	number	no	The width of the generated image in pixels

fn get_workers_ai_post_websocket_run_cf_deepgram_aura()

Open Websocket connection with @cf/deepgram/aura model.

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_1()

Open Websocket connection with @cf/deepgram/aura-1 model.

fn create_workers_ai_post_run_cf_deepgram_aura_1(queueRequest?: string, tags?: string, bit_rate?: number, container?: enum, encoding?: enum, sample_rate?: number, speaker?: enum, text: string)

Execute @cf/deepgram/aura-1 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
bit_rate?	number	no	The bitrate of the audio in bits per second. Choose from predefined ranges or...
container?	enum	no	Container specifies the file format wrapper for the output audio. The availab...
encoding?	enum	no	Encoding of the output audio.
sample_rate?	number	no	Sample Rate specifies the sample rate for the output audio. Based on the enco...
speaker?	enum	no	Speaker used to produce the audio.
text	string	yes	The text content to be converted to speech

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_1_internal()

Open Websocket connection with @cf/deepgram/aura-1-internal model.

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_2()

Open Websocket connection with @cf/deepgram/aura-2 model.

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_2_en()

Open Websocket connection with @cf/deepgram/aura-2-en model.

fn create_workers_ai_post_run_cf_deepgram_aura_2_en(queueRequest?: string, tags?: string, bit_rate?: number, container?: enum, encoding?: enum, sample_rate?: number, speaker?: enum, text?: string)

Execute @cf/deepgram/aura-2-en model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
bit_rate?	number	no	The bitrate of the audio in bits per second. Choose from predefined ranges or...
container?	enum	no	Container specifies the file format wrapper for the output audio. The availab...
encoding?	enum	no	Encoding of the output audio.
sample_rate?	number	no	Sample Rate specifies the sample rate for the output audio. Based on the enco...
speaker?	enum	no	Speaker used to produce the audio.
text?	string	no	The text content to be converted to speech

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_2_en_ws()

Open Websocket connection with @cf/deepgram/aura-2-en-ws model.

fn get_workers_ai_post_websocket_run_cf_deepgram_aura_2_es()

Open Websocket connection with @cf/deepgram/aura-2-es model.

fn create_workers_ai_post_run_cf_deepgram_aura_2_es(queueRequest?: string, tags?: string, bit_rate?: number, container?: enum, encoding?: enum, sample_rate?: number, speaker?: enum, text?: string)

Execute @cf/deepgram/aura-2-es model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
bit_rate?	number	no	The bitrate of the audio in bits per second. Choose from predefined ranges or...
container?	enum	no	Container specifies the file format wrapper for the output audio. The availab...
encoding?	enum	no	Encoding of the output audio.
sample_rate?	number	no	Sample Rate specifies the sample rate for the output audio. Based on the enco...
speaker?	enum	no	Speaker used to produce the audio.
text?	string	no	The text content to be converted to speech

fn get_workers_ai_post_websocket_run_cf_deepgram_flux()

Open Websocket connection with @cf/deepgram/flux model.

fn create_workers_ai_post_run_cf_deepgram_flux(queueRequest?: string, tags?: string, eager_eot_threshold?: string, encoding?: enum, eot_threshold?: string, eot_timeout_ms?: string, keyterm?: string, mip_opt_out?: enum, sample_rate?: string, tag?: string)

Execute @cf/deepgram/flux model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
eager_eot_threshold?	string	no	End-of-turn confidence required to fire an eager end-of-turn event. When set,...
encoding?	enum	no	Encoding of the audio stream. Currently only supports raw signed little-endia...
eot_threshold?	string	no	End-of-turn confidence required to finish a turn. Valid Values 0.5 - 0.9.
eot_timeout_ms?	string	no	A turn will be finished when this much time has passed after speech, regardle...
keyterm?	string	no	Keyterm prompting can improve recognition of specialized terminology. Pass mu...
mip_opt_out?	enum	no	Opts out requests from the Deepgram Model Improvement Program. Refer to Deepg...
sample_rate?	string	no	Sample rate of the audio stream in Hz.
tag?	string	no	Label your requests for the purpose of identification during usage reporting

fn get_workers_ai_post_websocket_run_cf_deepgram_nova_3()

Open Websocket connection with @cf/deepgram/nova-3 model.

fn create_workers_ai_post_run_cf_deepgram_nova_3(queueRequest?: string, tags?: string, audio: object, channels?: number, custom_intent?: string, custom_intent_mode?: enum, custom_topic?: string, custom_topic_mode?: enum, detect_entities?: boolean, detect_language?: boolean, diarize?: boolean, dictation?: boolean, encoding?: enum, endpointing?: string, extra?: string, filler_words?: boolean, interim_results?: boolean, keyterm?: string, keywords?: string, language?: string, measurements?: boolean, mip_opt_out?: boolean, mode?: enum, multichannel?: boolean, numerals?: boolean, paragraphs?: boolean, profanity_filter?: boolean, punctuate?: boolean, redact?: string, replace?: string, search?: string, sentiment?: boolean, smart_format?: boolean, topics?: boolean, utt_split?: number, utterance_end_ms?: boolean, utterances?: boolean, vad_events?: boolean)

Execute @cf/deepgram/nova-3 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
audio	object	yes
channels?	number	no	The number of channels in the submitted audio
custom_intent?	string	no	Custom intents you want the model to detect within your input audio if present
custom_intent_mode?	enum	no	Sets how the model will interpret intents submitted to the custom_intent para...
custom_topic?	string	no	Custom topics you want the model to detect within your input audio or text if...
custom_topic_mode?	enum	no	Sets how the model will interpret strings submitted to the custom_topic param...
detect_entities?	boolean	no	Identifies and extracts key entities from content in submitted audio
detect_language?	boolean	no	Identifies the dominant language spoken in submitted audio
diarize?	boolean	no	Recognize speaker changes. Each word in the transcript will be assigned a spe...
dictation?	boolean	no	Identify and extract key entities from content in submitted audio
encoding?	enum	no	Specify the expected encoding of your submitted audio
endpointing?	string	no	Indicates how long model will wait to detect whether a speaker has finished s...
extra?	string	no	Arbitrary key-value pairs that are attached to the API response for usage in ...
filler_words?	boolean	no	Filler Words can help transcribe interruptions in your audio, like 'uh' and 'um'
interim_results?	boolean	no	Specifies whether the streaming endpoint should provide ongoing transcription...
keyterm?	string	no	Key term prompting can boost or suppress specialized terminology and brands.
keywords?	string	no	Keywords can boost or suppress specialized terminology and brands.
language?	string	no	The BCP-47 language tag that hints at the primary spoken language. Depending ...
measurements?	boolean	no	Spoken measurements will be converted to their corresponding abbreviations.
mip_opt_out?	boolean	no	Opts out requests from the Deepgram Model Improvement Program. Refer to our D...
mode?	enum	no	Mode of operation for the model representing broad area of topic that will be...
multichannel?	boolean	no	Transcribe each audio channel independently.
numerals?	boolean	no	Numerals converts numbers from written format to numerical format.
paragraphs?	boolean	no	Splits audio into paragraphs to improve transcript readability.
profanity_filter?	boolean	no	Profanity Filter looks for recognized profanity and converts it to the neares...
punctuate?	boolean	no	Add punctuation and capitalization to the transcript.
redact?	string	no	Redaction removes sensitive information from your transcripts.
replace?	string	no	Search for terms or phrases in submitted audio and replaces them.
search?	string	no	Search for terms or phrases in submitted audio.
sentiment?	boolean	no	Recognizes the sentiment throughout a transcript or text.
smart_format?	boolean	no	Apply formatting to transcript output. When set to true, additional formattin...
topics?	boolean	no	Detect topics throughout a transcript or text.
utt_split?	number	no	Seconds to wait before detecting a pause between words in submitted audio.
utterance_end_ms?	boolean	no	Indicates how long model will wait to send an UtteranceEnd message after a wo...
utterances?	boolean	no	Segments speech into meaningful semantic units.
vad_events?	boolean	no	Indicates that speech has started. You'll begin receiving Speech Started mess...

fn get_workers_ai_post_websocket_run_cf_deepgram_nova_3_internal()

Open Websocket connection with @cf/deepgram/nova-3-internal model.

fn get_workers_ai_post_websocket_run_cf_deepgram_nova_3_ws()

Open Websocket connection with @cf/deepgram/nova-3-ws model.

fn workers_ai_post_run_cf_deepseek_ai_deepseek_math_7b_instruct(queueRequest?: string, tags?: string)

Execute @cf/deepseek-ai/deepseek-math-7b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_deepseek_ai_deepseek_r1_distill_qwen_32b(queueRequest?: string, tags?: string)

Execute @cf/deepseek-ai/deepseek-r1-distill-qwen-32b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_defog_sqlcoder_7b_2(queueRequest?: string, tags?: string)

Execute @cf/defog/sqlcoder-7b-2 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_facebook_bart_large_cnn(queueRequest?: string, tags?: string, input_text: string, max_length?: number)

Execute @cf/facebook/bart-large-cnn model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
input_text	string	yes	The text that you want the model to summarize
max_length?	number	no	The maximum length of the generated summary in tokens

fn create_workers_ai_post_run_cf_facebook_nonomni_bart_large_cnn(queueRequest?: string, tags?: string, input_text: string, max_length?: number)

Execute @cf/facebook/nonomni-bart-large-cnn model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
input_text	string	yes	The text that you want the model to summarize
max_length?	number	no	The maximum length of the generated summary in tokens

fn workers_ai_post_run_cf_facebook_nonomni_detr_resnet_50(queueRequest?: string, tags?: string)

Execute @cf/facebook/nonomni-detr-resnet-50 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_fblgit_una_cybertron_7b_v2_bf16(queueRequest?: string, tags?: string)

Execute @cf/fblgit/una-cybertron-7b-v2-bf16 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_google_embeddinggemma_300m(queueRequest?: string, tags?: string, text: union)

Execute @cf/google/embeddinggemma-300m model.

Argument	Type	Required
queueRequest?	string	no
tags?	string	no
text	union	yes

fn workers_ai_post_run_cf_google_gemma_2b_it_lora(queueRequest?: string, tags?: string)

Execute @cf/google/gemma-2b-it-lora model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_google_gemma_3_12b_it(queueRequest?: string, tags?: string)

Execute @cf/google/gemma-3-12b-it model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_google_gemma_4_26b_a4b_it(queueRequest?: string, tags?: string)

Execute @cf/google/gemma-4-26b-a4b-it model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_google_gemma_7b_it_lora(queueRequest?: string, tags?: string)

Execute @cf/google/gemma-7b-it-lora model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_google_nonomni_embeddinggemma_300m(queueRequest?: string, tags?: string, text: union)

Execute @cf/google/nonomni-embeddinggemma-300m model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
text	union	yes	Input text to embed. Can be a single string or a list of strings.

fn create_workers_ai_post_run_cf_huggingface_distilbert_sst_2_int8(queueRequest?: string, tags?: string, text: string)

Execute @cf/huggingface/distilbert-sst-2-int8 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
text	string	yes	The text that you want to classify

fn create_workers_ai_post_run_cf_huggingface_nonomni_distilbert_sst_2_int8(queueRequest?: string, tags?: string, text: string)

Execute @cf/huggingface/nonomni-distilbert-sst-2-int8 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
text	string	yes	The text that you want to classify

fn workers_ai_post_run_cf_ibm_granite_granite_4_0_h_micro(queueRequest?: string, tags?: string)

Execute @cf/ibm-granite/granite-4.0-h-micro model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_leonardo_lucid_origin(queueRequest?: string, tags?: string, guidance?: number, height?: number, num_steps?: number, prompt: string, seed?: number, steps?: number, width?: number)

Execute @cf/leonardo/lucid-origin model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate.
seed?	number	no	Random seed for reproducibility of the image generation
steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
width?	number	no	The width of the generated image in pixels

fn create_workers_ai_post_run_cf_leonardo_phoenix_1_0(queueRequest?: string, tags?: string, guidance?: number, height?: number, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, width?: number)

Execute @cf/leonardo/phoenix-1.0 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
negative_prompt?	string	no	Specify what to exclude from the generated images
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate.
seed?	number	no	Random seed for reproducibility of the image generation
width?	number	no	The width of the generated image in pixels

fn create_workers_ai_post_run_cf_lykon_dreamshaper_8_lcm(queueRequest?: string, tags?: string, guidance?: number, height?: number, image?: array, image_b64?: string, mask?: array, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, strength?: number, width?: number)

Execute @cf/lykon/dreamshaper-8-lcm model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
image?	array	no	For use with img2img tasks. An array of integers that represent the image dat...
image_b64?	string	no	For use with img2img tasks. A base64-encoded string of the input image
mask?	array	no	An array representing An array of integers that represent mask image data for...
negative_prompt?	string	no	Text describing elements to avoid in the generated image
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate
seed?	number	no	Random seed for reproducibility of the image generation
strength?	number	no	A value between 0 and 1 indicating how strongly to apply the transformation d...
width?	number	no	The width of the generated image in pixels

fn workers_ai_post_run_cf_meta_llama_llama_2_7b_chat_hf_lora(queueRequest?: string, tags?: string)

Execute @cf/meta-llama/llama-2-7b-chat-hf-lora model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_2_7b_chat_fp16(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-2-7b-chat-fp16 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_2_7b_chat_int8(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-2-7b-chat-int8 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_8b_instruct(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3-8b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_8b_instruct_awq(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3-8b-instruct-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_1_70b_instruct_fp8_fast(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.1-70b-instruct-fp8-fast model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_1_8b_instruct_awq(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.1-8b-instruct-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_1_8b_instruct_fp8(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.1-8b-instruct-fp8 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_1_8b_instruct_fp8_fast(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.1-8b-instruct-fp8-fast model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_2_11b_vision_instruct(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.2-11b-vision-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_2_1b_instruct(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.2-1b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_2_3b_instruct(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.2-3b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_3_3_70b_instruct_fp8_fast(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-3.3-70b-instruct-fp8-fast model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_meta_llama_4_scout_17b_16e_instruct(queueRequest?: string, tags?: string)

Execute @cf/meta/llama-4-scout-17b-16e-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_meta_llama_guard_3_8b(queueRequest?: string, tags?: string, max_tokens?: number, messages: array, response_format?: object, temperature?: number)

Execute @cf/meta/llama-guard-3-8b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
max_tokens?	number	no	The maximum number of tokens to generate in the response.
messages	array	yes	An array of message objects representing the conversation history.
response_format?	object	no	Dictate the output format of the generated response.
temperature?	number	no	Controls the randomness of the output; higher values produce more random resu...

fn workers_ai_post_run_cf_meta_m2m100_1_2b(queueRequest?: string, tags?: string)

Execute @cf/meta/m2m100-1.2b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_microsoft_nonomni_resnet_50(queueRequest?: string, tags?: string)

Execute @cf/microsoft/nonomni-resnet-50 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_microsoft_phi_2(queueRequest?: string, tags?: string)

Execute @cf/microsoft/phi-2 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_microsoft_resnet_50(queueRequest?: string, tags?: string)

Execute @cf/microsoft/resnet-50 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_mistral_mistral_7b_instruct_v0_1(queueRequest?: string, tags?: string)

Execute @cf/mistral/mistral-7b-instruct-v0.1 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_mistral_mistral_7b_instruct_v0_2_lora(queueRequest?: string, tags?: string)

Execute @cf/mistral/mistral-7b-instruct-v0.2-lora model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_mistralai_mistral_small_3_1_24b_instruct(queueRequest?: string, tags?: string)

Execute @cf/mistralai/mistral-small-3.1-24b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_moonshotai_kimi_k2_5(queueRequest?: string, tags?: string)

Execute @cf/moonshotai/kimi-k2.5 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_moonshotai_kimi_k2_6(queueRequest?: string, tags?: string)

Execute @cf/moonshotai/kimi-k2.6 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_moonshotai_kimi_k2_7_code(queueRequest?: string, tags?: string)

Execute @cf/moonshotai/kimi-k2.7-code model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_myshell_ai_melotts(queueRequest?: string, tags?: string, lang?: string, prompt: string)

Execute @cf/myshell-ai/melotts model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
lang?	string	no	The speech language (e.g., 'en' for English, 'fr' for French). Defaults to 'e...
prompt	string	yes	A text description of the audio you want to generate

fn workers_ai_post_run_cf_nvidia_nemotron_3_120b_a12b(queueRequest?: string, tags?: string)

Execute @cf/nvidia/nemotron-3-120b-a12b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn get_workers_ai_post_websocket_run_cf_nvidia_nemotron_speech_streaming_en_0_6b()

Open Websocket connection with @cf/nvidia/nemotron-speech-streaming-en-0.6b model.

fn workers_ai_post_run_cf_nvidia_nemotron_speech_streaming_en_0_6b(queueRequest?: string, tags?: string)

Execute @cf/nvidia/nemotron-speech-streaming-en-0.6b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_openai_gpt_oss_120b(queueRequest?: string, tags?: string)

Execute @cf/openai/gpt-oss-120b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_openai_gpt_oss_20b(queueRequest?: string, tags?: string)

Execute @cf/openai/gpt-oss-20b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_openai_whisper(queueRequest?: string, tags?: string)

Execute @cf/openai/whisper model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_openai_whisper_large_v3_turbo(queueRequest?: string, tags?: string, audio?: union, beam_size?: number, compression_ratio_threshold?: number, condition_on_previous_text?: boolean, hallucination_silence_threshold?: number, initial_prompt?: string, language?: string, log_prob_threshold?: number, no_speech_threshold?: number, prefix?: string, task?: string, vad_filter?: boolean)

Execute @cf/openai/whisper-large-v3-turbo model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
audio?	union	no
beam_size?	number	no	The number of beams to use in beam search decoding. Higher values may improve...
compression_ratio_threshold?	number	no	Threshold for filtering out segments with high compression ratio, which often...
condition_on_previous_text?	boolean	no	Whether to condition on previous text during transcription. Setting to false ...
hallucination_silence_threshold?	number	no	Optional threshold (in seconds) to skip silent periods that may cause halluci...
initial_prompt?	string	no	A text prompt to help provide context to the model on the contents of the audio.
language?	string	no	The language of the audio being transcribed or translated.
log_prob_threshold?	number	no	Threshold for filtering out segments with low average log probability, indica...
no_speech_threshold?	number	no	Threshold for detecting no-speech segments. Segments with no-speech probabili...
prefix?	string	no	The prefix appended to the beginning of the output of the transcription and c...
task?	string	no	Supported tasks are 'translate' or 'transcribe'.
vad_filter?	boolean	no	Preprocess the audio with a voice activity detection model.

fn workers_ai_post_run_cf_openai_whisper_tiny_en(queueRequest?: string, tags?: string)

Execute @cf/openai/whisper-tiny-en model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_openchat_openchat_3_5_0106(queueRequest?: string, tags?: string)

Execute @cf/openchat/openchat-3.5-0106 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_pfnet_plamo_embedding_1b(queueRequest?: string, tags?: string, text: union)

Execute @cf/pfnet/plamo-embedding-1b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
text	union	yes	Input text to embed. Can be a single string or a list of strings.

fn get_workers_ai_post_websocket_run_cf_pipecat_ai_smart_turn_v2()

Open Websocket connection with @cf/pipecat-ai/smart-turn-v2 model.

fn get_workers_ai_post_websocket_run_cf_pipecat_ai_smart_turn_v3()

Open Websocket connection with @cf/pipecat-ai/smart-turn-v3 model.

fn workers_ai_post_run_cf_qwen_qwen1_5_0_5b_chat(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen1.5-0.5b-chat model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_qwen_qwen1_5_1_8b_chat(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen1.5-1.8b-chat model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_qwen_qwen1_5_14b_chat_awq(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen1.5-14b-chat-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_qwen_qwen1_5_7b_chat_awq(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen1.5-7b-chat-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_qwen_qwen2_5_coder_32b_instruct(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen2.5-coder-32b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_qwen_qwen3_30b_a3b_fp8(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwen3-30b-a3b-fp8 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_qwen_qwen3_embedding_0_6b(queueRequest?: string, tags?: string, documents?: union, instruction?: string, queries?: union, text?: union)

Execute @cf/qwen/qwen3-embedding-0.6b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
documents?	union	no
instruction?	string	no	Optional instruction for the task
queries?	union	no
text?	union	no

fn workers_ai_post_run_cf_qwen_qwq_32b(queueRequest?: string, tags?: string)

Execute @cf/qwen/qwq-32b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn create_workers_ai_post_run_cf_runwayml_stable_diffusion_v1_5_img2img(queueRequest?: string, tags?: string, guidance?: number, height?: number, image?: array, image_b64?: string, mask?: array, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, strength?: number, width?: number)

Execute @cf/runwayml/stable-diffusion-v1-5-img2img model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
image?	array	no	For use with img2img tasks. An array of integers that represent the image dat...
image_b64?	string	no	For use with img2img tasks. A base64-encoded string of the input image
mask?	array	no	An array representing An array of integers that represent mask image data for...
negative_prompt?	string	no	Text describing elements to avoid in the generated image
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate
seed?	number	no	Random seed for reproducibility of the image generation
strength?	number	no	A value between 0 and 1 indicating how strongly to apply the transformation d...
width?	number	no	The width of the generated image in pixels

fn create_workers_ai_post_run_cf_runwayml_stable_diffusion_v1_5_inpainting(queueRequest?: string, tags?: string, guidance?: number, height?: number, image?: array, image_b64?: string, mask?: array, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, strength?: number, width?: number)

Execute @cf/runwayml/stable-diffusion-v1-5-inpainting model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
image?	array	no	For use with img2img tasks. An array of integers that represent the image dat...
image_b64?	string	no	For use with img2img tasks. A base64-encoded string of the input image
mask?	array	no	An array representing An array of integers that represent mask image data for...
negative_prompt?	string	no	Text describing elements to avoid in the generated image
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate
seed?	number	no	Random seed for reproducibility of the image generation
strength?	number	no	A value between 0 and 1 indicating how strongly to apply the transformation d...
width?	number	no	The width of the generated image in pixels

fn create_workers_ai_post_run_cf_stabilityai_stable_diffusion_xl_base_1_0(queueRequest?: string, tags?: string, guidance?: number, height?: number, image?: array, image_b64?: string, mask?: array, negative_prompt?: string, num_steps?: number, prompt: string, seed?: number, strength?: number, width?: number)

Execute @cf/stabilityai/stable-diffusion-xl-base-1.0 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no
guidance?	number	no	Controls how closely the generated image should adhere to the prompt; higher ...
height?	number	no	The height of the generated image in pixels
image?	array	no	For use with img2img tasks. An array of integers that represent the image dat...
image_b64?	string	no	For use with img2img tasks. A base64-encoded string of the input image
mask?	array	no	An array representing An array of integers that represent mask image data for...
negative_prompt?	string	no	Text describing elements to avoid in the generated image
num_steps?	number	no	The number of diffusion steps; higher values can improve quality but take longer
prompt	string	yes	A text description of the image you want to generate
seed?	number	no	Random seed for reproducibility of the image generation
strength?	number	no	A value between 0 and 1 indicating how strongly to apply the transformation d...
width?	number	no	The width of the generated image in pixels

fn get_workers_ai_post_websocket_run_cf_sven_test_pipe_http()

Open Websocket connection with @cf/sven/test-pipe-http model.

fn get_workers_ai_post_websocket_run_cf_test_hello_world_cog()

Open Websocket connection with @cf/test/hello-world-cog model.

fn workers_ai_post_run_cf_thebloke_discolm_german_7b_v1_awq(queueRequest?: string, tags?: string)

Execute @cf/thebloke/discolm-german-7b-v1-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_tiiuae_falcon_7b_instruct(queueRequest?: string, tags?: string)

Execute @cf/tiiuae/falcon-7b-instruct model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_tinyllama_tinyllama_1_1b_chat_v1_0(queueRequest?: string, tags?: string)

Execute @cf/tinyllama/tinyllama-1.1b-chat-v1.0 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_zai_org_glm_4_7_flash(queueRequest?: string, tags?: string)

Execute @cf/zai-org/glm-4.7-flash model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_cf_zai_org_glm_5_2(queueRequest?: string, tags?: string)

Execute @cf/zai-org/glm-5.2 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_google_gemma_7b_it(queueRequest?: string, tags?: string)

Execute @hf/google/gemma-7b-it model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_mistral_mistral_7b_instruct_v0_2(queueRequest?: string, tags?: string)

Execute @hf/mistral/mistral-7b-instruct-v0.2 model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_nexusflow_starling_lm_7b_beta(queueRequest?: string, tags?: string)

Execute @hf/nexusflow/starling-lm-7b-beta model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_nousresearch_hermes_2_pro_mistral_7b(queueRequest?: string, tags?: string)

Execute @hf/nousresearch/hermes-2-pro-mistral-7b model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_deepseek_coder_6_7b_base_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/deepseek-coder-6.7b-base-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_deepseek_coder_6_7b_instruct_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/deepseek-coder-6.7b-instruct-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_llama_2_13b_chat_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/llama-2-13b-chat-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_mistral_7b_instruct_v0_1_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/mistral-7b-instruct-v0.1-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_neural_chat_7b_v3_1_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/neural-chat-7b-v3-1-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_openhermes_2_5_mistral_7b_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/openhermes-2.5-mistral-7b-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_hf_thebloke_zephyr_7b_beta_awq(queueRequest?: string, tags?: string)

Execute @hf/thebloke/zephyr-7b-beta-awq model.

Argument	Type	Required	Description
queueRequest?	string	no
tags?	string	no

fn workers_ai_post_run_model(model_name: string)

Execute AI model

Argument	Type	Required	Description
model_name	string	yes

fn list_workers_ai_search_task()

Task Search

fn workers_ai_post_to_markdown()

Convert Files into Markdown

fn get_to_markdown_supported()

Get all converted formats supported

04Stats

100 / 100

Downloads

Archive size

118.1 KB

Has README or module doc2/2earned
README has a code example1/1earned
README is substantive1/1earned
Most symbols documented1/1earned
No slow types (deprecated)1/1earned
Dependencies pass trust audit2/2earned
Has description1/1earned
Platform support declared (or universal)2/2earned
License declared1/1earned
Verified public repository2/2earned

Repository

https://github.com/webframp/swamp-extensions

05Platforms

linux · x86_64 linux · aarch64 macOS · x86_64 macOS · aarch64

06Labels

#cloudflare #ai #inference #workers