Changelog

Happy Developer Week 2025! Workers AI is excited to announce a couple of new features and improvements available today. Check out our blog ↗ for all the announcement details.

We’re rolling out some in-place improvements to our models that can help speed up inference by 2-4x! Users of the models below will enjoy an automatic speed boost starting today:

• @cf/meta/llama-3.3-70b-instruct-fp8-fast gets a speed boost of 2-4x, leveraging techniques like speculative decoding, prefix caching, and an updated inference backend.
• @cf/baai/bge-small-en-v1.5, @cf/baai/bge-base-en-v1.5, @cf/baai/bge-large-en-v1.5 get an updated back end, which should improve inference times by 2x.
  • With the bge models, we’re also announcing a new parameter called pooling which can take cls or mean as options. We highly recommend using pooling: cls which will help generate more accurate embeddings. However, embeddings generated with cls pooling are not backwards compatible with mean pooling. For this to not be a breaking change, the default remains as mean pooling. Please specify pooling: cls to enjoy more accurate embeddings going forward.

We’re also excited to launch a few new models in our catalog to help round out your experience with Workers AI. We’ll be deprecating some older models in the future, so stay tuned for a deprecation announcement. Today’s new models include:

• @cf/mistralai/mistral-small-3.1-24b-instruct: a 24B parameter model achieving state-of-the-art capabilities comparable to larger models, with support for vision and tool calling.
• @cf/google/gemma-3-12b-it: well-suited for a variety of text generation and image understanding tasks, including question answering, summarization and reasoning, with a 128K context window, and multilingual support in over 140 languages.
• @cf/qwen/qwq-32b: a medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.
• @cf/qwen/qwen2.5-coder-32b-instruct: the current state-of-the-art open-source code LLM, with its coding abilities matching those of GPT-4o.

Introducing a new batch inference feature that allows you to send us an array of requests, which we will fulfill as fast as possible and send them back as an array. This is really helpful for large workloads such as summarization, embeddings, etc. where you don’t have a human-in-the-loop. Using the batch API will guarantee that your requests are fulfilled eventually, rather than erroring out if we don’t have enough capacity at a given time.

Check out the tutorial to get started! Models that support batch inference today include:

• @cf/meta/llama-3.3-70b-instruct-fp8-fast
• @cf/baai/bge-small-en-v1.5
• @cf/baai/bge-base-en-v1.5
• @cf/baai/bge-large-en-v1.5
• @cf/baai/bge-m3
• @cf/meta/m2m100-1.2b

We’ve upgraded our LoRA experience to include 8 newer models, and can support ranks of up to 32 with a 300MB safetensors file limit (previously limited to rank of 8 and 100MB safetensors) Check out our LoRAs page to get started. Models that support LoRAs now include:

• @cf/meta/llama-3.2-11b-vision-instruct
• @cf/meta/llama-3.3-70b-instruct-fp8-fast
• @cf/meta/llama-guard-3-8b
• @cf/meta/llama-3.1-8b-instruct-fast (coming soon)
• @cf/deepseek-ai/deepseek-r1-distill-qwen-32b (coming soon)
• @cf/qwen/qwen2.5-coder-32b-instruct
• @cf/qwen/qwq-32b
• @cf/mistralai/mistral-small-3.1-24b-instruct
• @cf/google/gemma-3-12b-it

Document conversion plays an important role when designing and developing AI applications and agents. Workers AI now provides the toMarkdown utility method that developers can use to for quick, easy, and convenient conversion and summary of documents in multiple formats to Markdown language.

You can call this new tool using a binding by calling env.AI.toMarkdown() or the using the REST API endpoint.

In this example, we fetch a PDF document and an image from R2 and feed them both to env.AI.toMarkdown(). The result is a list of converted documents. Workers AI models are used automatically to detect and summarize the image.

import { Env } from "./env";

export default {
	async fetch(request: Request, env: Env, ctx: ExecutionContext) {
		// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/somatosensory.pdf
		const pdf = await env.R2.get("somatosensory.pdf");

		// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/cat.jpeg
		const cat = await env.R2.get("cat.jpeg");

		return Response.json(
			await env.AI.toMarkdown([
				{
					name: "somatosensory.pdf",
					blob: new Blob([await pdf.arrayBuffer()], {
						type: "application/octet-stream",
					}),
				},
				{
					name: "cat.jpeg",
					blob: new Blob([await cat.arrayBuffer()], {
						type: "application/octet-stream",
					}),
				},
			]),
		);
	},
};

This is the result:

[
	{
		"name": "somatosensory.pdf",
		"mimeType": "application/pdf",
		"format": "markdown",
		"tokens": 0,
		"data": "# somatosensory.pdf\n## Metadata\n- PDFFormatVersion=1.4\n- IsLinearized=false\n- IsAcroFormPresent=false\n- IsXFAPresent=false\n- IsCollectionPresent=false\n- IsSignaturesPresent=false\n- Producer=Prince 20150210 (www.princexml.com)\n- Title=Anatomy of the Somatosensory System\n\n## Contents\n### Page 1\nThis is a sample document to showcase..."
	},
	{
		"name": "cat.jpeg",
		"mimeType": "image/jpeg",
		"format": "markdown",
		"tokens": 0,
		"data": "The image is a close-up photograph of Grumpy Cat, a cat with a distinctive grumpy expression and piercing blue eyes. The cat has a brown face with a white stripe down its nose, and its ears are pointed upright. Its fur is light brown and darker around the face, with a pink nose and mouth. The cat's eyes are blue and slanted downward, giving it a perpetually grumpy appearance. The background is blurred, but it appears to be a dark brown color. Overall, the image is a humorous and iconic representation of the popular internet meme character, Grumpy Cat. The cat's facial expression and posture convey a sense of displeasure or annoyance, making it a relatable and entertaining image for many people."
	}
]

See Markdown Conversion for more information on supported formats, REST API and pricing.

Workers AI is excited to add 4 new models to the catalog, including 2 brand new classes of models with a text-to-speech and reranker model. Introducing:

• @cf/baai/bge-m3 - a multi-lingual embeddings model that supports over 100 languages. It can also simultaneously perform dense retrieval, multi-vector retrieval, and sparse retrieval, with the ability to process inputs of different granularities.
• @cf/baai/bge-reranker-base - our first reranker model! Rerankers are a type of text classification model that takes a query and context, and outputs a similarity score between the two. When used in RAG systems, you can use a reranker after the initial vector search to find the most relevant documents to return to a user by reranking the outputs.
• @cf/openai/whisper-large-v3-turbo - a faster, more accurate speech-to-text model. This model was added earlier but is graduating out of beta with pricing included today.
• @cf/myshell-ai/melotts - our first text-to-speech model that allows users to generate an MP3 with voice audio from inputted text.

Pricing is available for each of these models on the Workers AI pricing page.

This docs update includes a few minor bug fixes to the model schema for llama-guard, llama-3.2-1b, which you can review on the product changelog.

Try it out and let us know what you think! Stay tuned for more models in the coming days.

Workers AI now supports structured JSON outputs with JSON mode, which allows you to request a structured output response when interacting with AI models.

This makes it much easier to retrieve structured data from your AI models, and avoids the (error prone!) need to parse large unstructured text responses to extract your data.

JSON mode in Workers AI is compatible with the OpenAI SDK's structured outputs ↗ response_format API, which can be used directly in a Worker:

import { OpenAI } from "openai";

// Define your JSON schema for a calendar event
const CalendarEventSchema = {
	type: "object",
	properties: {
		name: { type: "string" },
		date: { type: "string" },
		participants: { type: "array", items: { type: "string" } },
	},
	required: ["name", "date", "participants"],
};

export default {
	async fetch(request, env) {
		const client = new OpenAI({
			apiKey: env.OPENAI_API_KEY,
			// Optional: use AI Gateway to bring logs, evals & caching to your AI requests
			// https://developers.cloudflare.com/ai-gateway/usage/providers/openai/
			// baseUrl: "https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/openai"
		});

		const response = await client.chat.completions.create({
			model: "gpt-4o-2024-08-06",
			messages: [
				{ role: "system", content: "Extract the event information." },
				{
					role: "user",
					content: "Alice and Bob are going to a science fair on Friday.",
				},
			],
			// Use the `response_format` option to request a structured JSON output
			response_format: {
				// Set json_schema and provide ra schema, or json_object and parse it yourself
				type: "json_schema",
				schema: CalendarEventSchema, // provide a schema
			},
		});

		// This will be of type CalendarEventSchema
		const event = response.choices[0].message.parsed;

		return Response.json({
			calendar_event: event,
		});
	},
};

import { OpenAI } from "openai";

interface Env {
	OPENAI_API_KEY: string;
}

// Define your JSON schema for a calendar event
const CalendarEventSchema = {
	type: "object",
	properties: {
		name: { type: "string" },
		date: { type: "string" },
		participants: { type: "array", items: { type: "string" } },
	},
	required: ["name", "date", "participants"],
};

export default {
	async fetch(request: Request, env: Env) {
		const client = new OpenAI({
			apiKey: env.OPENAI_API_KEY,
			// Optional: use AI Gateway to bring logs, evals & caching to your AI requests
			// https://developers.cloudflare.com/ai-gateway/usage/providers/openai/
			// baseUrl: "https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/openai"
		});

		const response = await client.chat.completions.create({
			model: "gpt-4o-2024-08-06",
			messages: [
				{ role: "system", content: "Extract the event information." },
				{
					role: "user",
					content: "Alice and Bob are going to a science fair on Friday.",
				},
			],
			// Use the `response_format` option to request a structured JSON output
			response_format: {
				// Set json_schema and provide ra schema, or json_object and parse it yourself
				type: "json_schema",
				schema: CalendarEventSchema, // provide a schema
			},
		});

		// This will be of type CalendarEventSchema
		const event = response.choices[0].message.parsed;

		return Response.json({
			calendar_event: event,
		});
	},
};

To learn more about JSON mode and structured outputs, visit the Workers AI documentation.

We've updated the Workers AI text generation models to include context windows and limits definitions and changed our APIs to estimate and validate the number of tokens in the input prompt, not the number of characters.

This update allows developers to use larger context windows when interacting with Workers AI models, which can lead to better and more accurate results.

Our catalog page provides more information about each model's supported context window.

We've updated the Workers AI pricing to include the latest models and how model usage maps to Neurons.

• Each model's core input format(s) (tokens, audio seconds, images, etc) now include mappings to Neurons, making it easier to understand how your included Neuron volume is consumed and how you are charged at scale
• Per-model pricing, instead of the previous bucket approach, allows us to be more flexible on how models are charged based on their size, performance and capabilities. As we optimize each model, we can then pass on savings for that model.
• You will still only pay for what you consume: Workers AI inference is serverless, and not billed by the hour.

Going forward, models will be launched with their associated Neuron costs, and we'll be updating the Workers AI dashboard and API to reflect consumption in both raw units and Neurons. Visit the Workers AI pricing page to learn more about Workers AI pricing.