Cloudflare Docs
Workers AI
Edit this page
Report an issue with this page
Log into the Cloudflare dashboard
Set theme to dark (⇧+D)

Models

Browse our entire catalog of models:

​​ Automatic Speech Recognition

Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text.

ModelDescription
whisperAutomatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data
whisper-tiny-en BetaWhisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.

​​ Image Classification

Image classification models take an image input and assigns it labels or classes.

ModelDescription
resnet-5050 layers deep image classification CNN trained on more than 1M images from ImageNet

​​ Image-to-Text

Image to text models output a text from a given image. Image captioning or optical character recognition can be considered as the most common applications of image to text.

ModelDescription
llava-1.5-7b-hf BetaLLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.
uform-gen2-qwen-500m BetaUForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.

​​ Object Detection

Object detection models can detect instances of objects like persons, faces, license plates, or others in an image. This task takes an image as input and returns a list of detected objects, each one containing a label, a probability score, and its surrounding box coordinates.

ModelDescription
detr-resnet-50 BetaDEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images).

​​ Summarization

Summarization is the task of producing a shorter version of a document while preserving its important information. Some models can extract text from the original input, while other models can generate entirely new text.

ModelDescription
bart-large-cnn BetaBART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.

​​ Text Classification

Sentiment analysis or text classification is a common NLP task that classifies a text input into labels or classes.

ModelDescription
distilbert-sst-2-int8Distilled BERT model that was finetuned on SST-2 for sentiment classification

​​ Text Embeddings

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).

ModelDescription
bge-base-en-v1.5BAAI general embedding (bge) models transform any given text into a compact vector
bge-large-en-v1.5BAAI general embedding (bge) models transform any given text into a compact vector
bge-small-en-v1.5BAAI general embedding (bge) models transform any given text into a compact vector

​​ Text Generation

Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks.

ModelDescription
llama-2-7b-chat-fp16Full precision (fp16) generative text model with 7 billion parameters from Meta
llama-2-7b-chat-int8 Planned deprecationQuantized (int8) generative text model with 7 billion parameters from Meta
mistral-7b-instruct-v0.1 LoRAInstruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters
deepseek-coder-6.7b-base-awq BetaDeepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.
deepseek-coder-6.7b-instruct-awq BetaDeepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.
deepseek-math-7b-base BetaDeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.
deepseek-math-7b-instruct BetaDeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.
discolm-german-7b-v1-awq BetaDiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
falcon-7b-instruct BetaFalcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.
gemma-2b-it-lora Beta LoRAThis is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
gemma-7b-it Beta LoRAGemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.
gemma-7b-it-lora Beta LoRAThis is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
hermes-2-pro-mistral-7b Beta Function callingHermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
llama-2-13b-chat-awq BetaLlama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.
llama-2-7b-chat-hf-lora Beta LoRAThis is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format.
llama-3-8b-instruct BetaGeneration over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.
llama-3-8b-instruct-awq BetaQuantized (int4) generative text model with 8 billion parameters from Meta.
llamaguard-7b-awq BetaLlama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.
mistral-7b-instruct-v0.1-awq BetaMistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.
mistral-7b-instruct-v0.2 Beta LoRAThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1: 32k context window (vs 8k context in v0.1), rope-theta = 1e6, and no Sliding-Window Attention.
mistral-7b-instruct-v0.2-lora Beta LoRAThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
neural-chat-7b-v3-1-awq BetaThis model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.
openchat-3.5-0106 BetaOpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.
openhermes-2.5-mistral-7b-awq BetaOpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
phi-2 BetaPhi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.
qwen1.5-0.5b-chat BetaQwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
qwen1.5-1.8b-chat BetaQwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
qwen1.5-14b-chat-awq BetaQwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
qwen1.5-7b-chat-awq BetaQwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
sqlcoder-7b-2 BetaThis model is intended to be used by non-technical users to understand data inside their SQL databases.
starling-lm-7b-beta BetaWe introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).
tinyllama-1.1b-chat-v1.0 BetaThe TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.
una-cybertron-7b-v2-bf16 BetaCybertron 7B v2 is a 7B MistralAI based model, best on it’s series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
zephyr-7b-beta-awq BetaZephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.

​​ Text-to-Image

Generates images from input text. These models can be used to generate and modify images based on text prompts.

ModelDescription
dreamshaper-8-lcm BetaStable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.
stable-diffusion-v1-5-img2img BetaStable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images. Img2img generate a new image from an input image with Stable Diffusion.
stable-diffusion-v1-5-inpainting BetaStable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask.
stable-diffusion-xl-base-1.0 BetaDiffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.
stable-diffusion-xl-lightning BetaSDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps.

​​ Translation

Translation models convert a sequence of text from one language to another.

ModelDescription
m2m100-1.2bMultilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation