run

Creates, updates, deletes, gets or lists a run resource.

Overview

Name	run
Type	Resource
Id	cloudflare.ai.run

Supported models

Set model_name to one of the following models:

Text Generation (55 models)

@cf/aisingapore/gemma-sea-lion-v4-27b-it
@cf/deepseek-ai/deepseek-math-7b-instruct
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
@cf/defog/sqlcoder-7b-2
@cf/fblgit/una-cybertron-7b-v2-bf16
@cf/google/gemma-2b-it-lora
@cf/google/gemma-3-12b-it
@cf/google/gemma-7b-it-lora
@cf/ibm-granite/granite-4.0-h-micro
@cf/meta-llama/llama-2-7b-chat-hf-lora
@cf/meta/llama-2-7b-chat-fp16
@cf/meta/llama-2-7b-chat-int8
@cf/meta/llama-3-8b-instruct
@cf/meta/llama-3-8b-instruct-awq
@cf/meta/llama-3.1-70b-instruct-fp8-fast
@cf/meta/llama-3.1-8b-instruct-awq
@cf/meta/llama-3.1-8b-instruct-fp8
@cf/meta/llama-3.1-8b-instruct-fp8-fast
@cf/meta/llama-3.2-11b-vision-instruct
@cf/meta/llama-3.2-1b-instruct
@cf/meta/llama-3.2-3b-instruct
@cf/meta/llama-3.3-70b-instruct-fp8-fast
@cf/meta/llama-4-scout-17b-16e-instruct
@cf/meta/llama-guard-3-8b
@cf/microsoft/phi-2
@cf/mistral/mistral-7b-instruct-v0.1
@cf/mistral/mistral-7b-instruct-v0.2-lora
@cf/mistralai/mistral-small-3.1-24b-instruct
@cf/moonshotai/kimi-k2.5
@cf/nvidia/nemotron-3-120b-a12b
@cf/openai/gpt-oss-120b
@cf/openai/gpt-oss-20b
@cf/openchat/openchat-3.5-0106
@cf/qwen/qwen1.5-0.5b-chat
@cf/qwen/qwen1.5-1.8b-chat
@cf/qwen/qwen1.5-14b-chat-awq
@cf/qwen/qwen1.5-7b-chat-awq
@cf/qwen/qwen2.5-coder-32b-instruct
@cf/qwen/qwen3-30b-a3b-fp8
@cf/qwen/qwq-32b
@cf/thebloke/discolm-german-7b-v1-awq
@cf/tiiuae/falcon-7b-instruct
@cf/tinyllama/tinyllama-1.1b-chat-v1.0
@cf/zai-org/glm-4.7-flash
@hf/google/gemma-7b-it
@hf/mistral/mistral-7b-instruct-v0.2
@hf/nexusflow/starling-lm-7b-beta
@hf/nousresearch/hermes-2-pro-mistral-7b
@hf/thebloke/deepseek-coder-6.7b-base-awq
@hf/thebloke/deepseek-coder-6.7b-instruct-awq
@hf/thebloke/llama-2-13b-chat-awq
@hf/thebloke/mistral-7b-instruct-v0.1-awq
@hf/thebloke/neural-chat-7b-v3-1-awq
@hf/thebloke/openhermes-2.5-mistral-7b-awq
@hf/thebloke/zephyr-7b-beta-awq

Text Embeddings (12 models)

@cf/baai/bge-base-en-v1.5
@cf/baai/bge-large-en-v1.5
@cf/baai/bge-m3
@cf/baai/bge-small-en-v1.5
@cf/baai/nonomni-bge-base-en-v1.5
@cf/baai/nonomni-bge-large-en-v1.5
@cf/baai/nonomni-bge-m3
@cf/baai/nonomni-bge-small-en-v1.5
@cf/google/embeddinggemma-300m
@cf/google/nonomni-embeddinggemma-300m
@cf/pfnet/plamo-embedding-1b
@cf/qwen/qwen3-embedding-0.6b

Speech to Text (3 models)

@cf/deepgram/flux
@cf/deepgram/nova-3
@cf/openai/whisper-large-v3-turbo

Translation (3 models)

@cf/ai4bharat/indictrans2-en-indic-1B
@cf/ai4bharat/nonomni-indictrans2-en-indic-1b
@cf/meta/m2m100-1.2b

Summarization (2 models)

@cf/facebook/bart-large-cnn
@cf/facebook/nonomni-bart-large-cnn

Text to Image (11 models)

@cf/black-forest-labs/flux-1-schnell
@cf/black-forest-labs/flux-2-dev
@cf/black-forest-labs/flux-2-klein-4b
@cf/black-forest-labs/flux-2-klein-9b
@cf/bytedance/stable-diffusion-xl-lightning
@cf/leonardo/lucid-origin
@cf/leonardo/phoenix-1.0
@cf/lykon/dreamshaper-8-lcm
@cf/runwayml/stable-diffusion-v1-5-img2img
@cf/runwayml/stable-diffusion-v1-5-inpainting
@cf/stabilityai/stable-diffusion-xl-base-1.0

Text to Speech (4 models)

@cf/deepgram/aura-1
@cf/deepgram/aura-2-en
@cf/deepgram/aura-2-es
@cf/myshell-ai/melotts

Text Classification (2 models)

@cf/huggingface/distilbert-sst-2-int8
@cf/huggingface/nonomni-distilbert-sst-2-int8

Reranking (1 model)

@cf/baai/bge-reranker-base

The task-family resources above give these models typed result columns - prefer them over run where one exists. Binary-input models (@cf/facebook/nonomni-detr-resnet-50, @cf/microsoft/nonomni-resnet-50, @cf/microsoft/resnet-50, @cf/openai/whisper, @cf/openai/whisper-tiny-en) take a raw request body and are exposed as exec methods on this resource instead of SELECT.

Fields

The following fields are returned by SELECT queries:

run

Model response

Name	Datatype	Description
data	array	Embedding vectors, one per input text.
model	string	Echo of the model name, where reported.
pooling	string	Pooling method used (cls or mean), where applicable.
response	string	The generated text response from the model.
shape	array	Dimensions of the returned embedding matrix.
summary	string	The summarized text.
text	string	The transcribed text.
tool_calls	array	Tool call requests emitted by the model, if tools were provided.
transcription_info	object	Model/language detail, where reported.
translated_text	string	The translated text.
usage	object	Token usage counts (prompt_tokens, completion_tokens, total_tokens).
vtt	string	WebVTT formatted transcription, where reported.
word_count	number	Number of words in the transcription, where reported.
words	array	Per-word timing detail, where reported.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
run	select	account_id, model_name		This endpoint provides users with the capability to run specific AI models on-demand. By submitting the required input data, users can receive real-time predictions or results generated by the chosen AI model. The endpoint supports various AI model types, ensuring flexibility and adaptability for diverse use cases. Model specific inputs available in Cloudflare Docs.
nonomni_detr_resnet_50	exec	account_id	queueRequest, tags	Runs inference on the @cf/facebook/nonomni-detr-resnet-50 model.
nonomni_resnet_50	exec	account_id	queueRequest, tags	Runs inference on the @cf/microsoft/nonomni-resnet-50 model.
resnet_50	exec	account_id	queueRequest, tags	Runs inference on the @cf/microsoft/resnet-50 model.
whisper	exec	account_id	queueRequest, tags	Runs inference on the @cf/openai/whisper model.
whisper_tiny_en	exec	account_id	queueRequest, tags	Runs inference on the @cf/openai/whisper-tiny-en model.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
account_id	string	The Cloudflare account ID.
model_name	string
queueRequest	string
tags	string

SELECT examples

run

This endpoint provides users with the capability to run specific AI models on-demand. By submitting the required input data, users can receive real-time predictions or results generated by the chosen AI model. The endpoint supports various AI model types, ensuring flexibility and adaptability for diverse use cases. Model specific inputs available in Cloudflare Docs.

SELECT
response,
usage,
data,
shape,
text,
translated_text,
summary
FROM cloudflare.ai.run
WHERE account_id = '{{ account_id }}' -- required
AND model_name = '{{ model_name }}' -- required
AND prompt = '{{ prompt }}' -- model input
;

Lifecycle Methods

nonomni_detr_resnet_50

Runs inference on the @cf/facebook/nonomni-detr-resnet-50 model.

EXEC cloudflare.ai.run.nonomni_detr_resnet_50 
@account_id='{{ account_id }}' --required, 
@queueRequest='{{ queueRequest }}', 
@tags='{{ tags }}'
;

nonomni_resnet_50

Runs inference on the @cf/microsoft/nonomni-resnet-50 model.

EXEC cloudflare.ai.run.nonomni_resnet_50 
@account_id='{{ account_id }}' --required, 
@queueRequest='{{ queueRequest }}', 
@tags='{{ tags }}'
;

resnet_50

Runs inference on the @cf/microsoft/resnet-50 model.

EXEC cloudflare.ai.run.resnet_50 
@account_id='{{ account_id }}' --required, 
@queueRequest='{{ queueRequest }}', 
@tags='{{ tags }}'
;

whisper

Runs inference on the @cf/openai/whisper model.

EXEC cloudflare.ai.run.whisper 
@account_id='{{ account_id }}' --required, 
@queueRequest='{{ queueRequest }}', 
@tags='{{ tags }}'
;

whisper_tiny_en

Runs inference on the @cf/openai/whisper-tiny-en model.

EXEC cloudflare.ai.run.whisper_tiny_en 
@account_id='{{ account_id }}' --required, 
@queueRequest='{{ queueRequest }}', 
@tags='{{ tags }}'
;