Workers AI Models
Last updated Aug 12, 2026
Model not available
is deprecated, removed, or not found. Choose an available model from the catalog below.
Looking for more models, including external providers?
Check out the unified AI model catalog.
Task TypesCapabilitiesAuthorsNewest first
We found 73 modelsClear filters
Compare models
Compare up to three models.
Close
Clear comparison
No models found
Try a different search term, or broaden your search by removing filters.
s<h3>apertus-v1.5-8b</h3>swiss-aiText Generation Apertus 1.5 is an 8B parameter language model designed to advance the state of multilingual, multimodal, fully open, and transparent AI. The models support a wide range of languages, handle contexts of up to 262,144 tokens, and it uses only fully open training data whilst delivering performance comparable to other models of similar size. For access, please fill out this form: https://forms.gle/kgvmkr6ucHN3xNuH6
Compare
<h3>aura-1</h3>DeepgramText-to-Speech Aura is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.
Compare
<h3>aura-2-en</h3>DeepgramText-to-Speech Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.
Compare
<h3>aura-2-es</h3>DeepgramText-to-Speech Aura-2 is a context-aware text-to-speech (TTS) model that applies natural pacing, expressiveness, and fillers based on the context of the provided text. The quality of your text input directly impacts the naturalness of the audio output.
Compare
<h3>bge-base-en-v1.5</h3>BAAIText Embeddings BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector
Compare
<h3>bge-large-en-v1.5</h3>BAAIText Embeddings BAAI general embedding (Large) model that transforms any given text into a 1024-dimensional vector
Compare
<h3>bge-m3</h3>BAAIText Embeddings Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.
Compare
<h3>bge-reranker-base</h3>BAAIText Classification Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
Compare
<h3>bge-small-en-v1.5</h3>BAAIText Embeddings BAAI general embedding (Small) model that transforms any given text into a 384-dimensional vector
Compare
Pinned<h3>clairic</h3>CloudflareText Generation Clairic is a System One-style model that can extract, compute, estimate, and forecast values from inputs. It is strongly typed and outputs confidence scores and probabilities against its outputs. This model is in preview from the Cloudflare Workers AI team.
Compare
Pinned<h3>clef</h3>CloudflareText Generation Clef is a 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
Compare
Pinned<h3>clef-flash</h3>CloudflareText Generation Clef-flash is a fast 9B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
Compare
Pinned<h3>clef-omni</h3>CloudflareText Generation Clef-omni is a multimodal decision model built on a 30B-parameter mixture-of-experts (3B active) backbone. It turns a state and a schema of typed questions into decisions, reads the state as text, JSON, images, audio, or video, and returns a probability for every allowed option of every question.
Compare
<h3>deepseek-r1-distill-qwen-32b</h3>DeepSeekText Generation DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
Compare
<h3>deepseek-v4-flash-0731</h3>DeepSeekText Generation DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.
Compare
<h3>deepseek-v4-pro-0813</h3>DeepSeekText Generation DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek with a one million token context window, built for long-horizon agentic workflows and complex, multi-step problem-solving
Compare
<h3>deepseek-v4.1-flash-1017</h3>DeepSeekText Generation We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.
Compare
<h3>distilbert-sst-2-int8</h3>HuggingFaceText Classification Distilled BERT model that was finetuned on SST-2 for sentiment classification
Compare
l<h3>dreamshaper-8-lcm</h3>lykonText-to-Image Stable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.
Compare
<h3>embeddinggemma-300m</h3>BetaGoogleText Embeddings EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.
Compare
u<h3>eurollm-9b-it</h3>utter-projectText Generation EuroLLM-9B is a 9B parameter model trained on 4 trillion tokens divided across the considered languages and several data sources: Web data, parallel data (en-xx and xx-en), and high-quality datasets. For access, please fill out this form: https://forms.gle/kgvmkr6ucHN3xNuH6
Compare
<h3>flux</h3>DeepgramAutomatic Speech Recognition Flux is the first conversational speech recognition model built specifically for voice agents.
Compare
<h3>flux-1-schnell</h3>Black Forest LabsText-to-Image FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.
Compare
<h3>flux-2-dev</h3>Black Forest LabsText-to-Image FLUX.2 [dev] is an image model from Black Forest Labs where you can generate highly realistic and detailed images, with multi-reference support.
Compare
<h3>flux-2-klein-4b</h3>Black Forest LabsText-to-Image FLUX.2 [klein] is an ultra-fast, distilled image model. It unifies image generation and editing in a single model, delivering state-of-the-art quality enabling interactive workflows, real-time previews, and latency-critical applications.
Compare
<h3>flux-2-klein-9b</h3>Black Forest LabsText-to-Image FLUX.2 [klein] 9B is a 9 billion parameter model that can generate images from text descriptions and supports multi-reference editing capabilities.
Compare
<h3>gemma-2b-it-lora</h3>BetaGoogleText Generation This 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.
Compare
<h3>gemma-4-26b-a4b-it</h3>GoogleText Generation Gemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.
Compare
<h3>gemma-7b-it-lora</h3>BetaGoogleText Generation This 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.
Compare
a<h3>gemma-sea-lion-v4-27b-it</h3>aisingaporeText Generation SEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
Compare
<h3>glm-4.7-flash</h3>Zhipu AIText Generation GLM-4.7-Flash is a fast and efficient multilingual text generation model with a 131,072 token context window. Optimized for dialogue, instruction-following, and multi-turn tool calling across 100+ languages.
Compare
<h3>glm-5.2</h3>Zhipu AIText Generation Z.ai's flagship agentic coding model
Compare
<h3>glm-5.3</h3>Zhipu AIText Generation GLM-5.3 is Z.ai's flagship agentic coding model, pairing a 1M-token context window with reasoning, function calling, and structured outputs to power multi-step, tool-driven development workflows.
Compare
<h3>glm-5.3-flash</h3>Zhipu AIText Generation The first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks.
Compare
<h3>gpt-oss-120b</h3>OpenAIText Generation OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.
Compare
<h3>gpt-oss-20b</h3>OpenAIText Generation OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.
Compare
<h3>granite-4.0-h-micro</h3>IBMText Generation Granite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. These efficiencies make the models well-suited for a wide range of use cases like retrieval-augmented generation (RAG), multi-agent workflows, and edge deployments.
Compare
a<h3>indictrans2-en-indic-1B</h3>ai4bharatTranslation IndicTrans2 is the first open-source transformer-based multilingual NMT model that supports high-quality translations across all the 22 scheduled Indic languages
Compare
<h3>kimi-k2.6</h3>Moonshot AIText Generation Kimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.
我的书签
添加书签
移除书签
