Products · Developer platform
Workers AI
Run AI models in Workers, Pages, or via API
Pricing and limits
Pricing
As of Nov 3, 2026, from Cloudflare's docs, last updated there Oct 20, 2026. Licensed CC BY 4.0; navigation removed.
Note
Workers AI has updated pricing to be more granular, with per-model unit-based pricing presented, but still billing in neurons in the back end.
Workers AI is included in both the Free and Paid Workers plans and is priced at $0.011 per 1,000 Neurons.
Our free allocation allows anyone to use a total of 10,000 Neurons per day at no charge. To use more than 10,000 Neurons per day, you need to sign up for the Workers Paid plan. On Workers Paid, you will be charged at $0.011 / 1,000 Neurons for any usage above the free allocation of 10,000 Neurons per day.
You can monitor your Neuron usage in the Cloudflare Workers AI dashboard ↗︎.
All limits reset daily at 00:00 UTC. If you exceed any one of the above limits, further operations will fail with an error.
| Free allocation |
Pricing | |
|---|---|---|
| Workers Free | 10,000 Neurons per day | N/A - Upgrade to Workers Paid |
| Workers Paid | 10,000 Neurons per day | $0.011 / 1,000 Neurons |
Note
Some models require a paid billing method. This applies to @cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.7-code, @cf/zai-org/glm-5.2, @cf/zai-org/glm-5.3, @cf/zai-org/glm-5.3-flash, @cf/deepseek-ai/deepseek-v4-flash-0731, @cf/deepseek-ai/deepseek-v4.1-flash-1017, and @cf/deepseek-ai/deepseek-v4-pro-0813. You can access these models with either the Workers Paid plan or prepaid AI Gateway credits.
Pay with AI Gateway credits
You can use prepaid AI Gateway credits to pay for Workers AI inference. Set the gateway's Workers AI billing setting to Unified billing, then specify that gateway in the AI binding or REST API request.
Requests to frontier models that use prepaid credits receive higher rate limits.
What are Neurons?
Neurons are our way of measuring AI outputs across different models, representing the GPU compute needed to perform your request. Our serverless model allows you to pay only for what you use without having to worry about renting, managing, or scaling GPUs.
Note
The Price in Tokens column is equivalent to the Price in Neurons column - the different units are displayed so you can easily compare and understand pricing.
LLM model pricing
| Model | Price in Tokens | Price in Neurons |
|---|---|---|
| @cf/meta/llama-3.2-1b-instruct | $0.027 per M input tokens $0.201 per M output tokens |
2457 neurons per M input tokens 18252 neurons per M output tokens |
| @cf/meta/llama-3.2-3b-instruct | $0.051 per M input tokens $0.335 per M output tokens |
4625 neurons per M input tokens 30475 neurons per M output tokens |
| @cf/meta/llama-3.1-8b-instruct-fp8-fast | $0.045 per M input tokens $0.384 per M output tokens |
4119 neurons per M input tokens 34868 neurons per M output tokens |
| @cf/meta/llama-3.2-11b-vision-instruct | $0.049 per M input tokens $0.676 per M output tokens |
4410 neurons per M input tokens 61493 neurons per M output tokens |
| @cf/meta/llama-3.1-70b-instruct-fp8-fast | $0.293 per M input tokens $2.253 per M output tokens |
26668 neurons per M input tokens 204805 neurons per M output tokens |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | $0.293 per M input tokens $2.253 per M output tokens |
26668 neurons per M input tokens 204805 neurons per M output tokens |
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | $0.497 per M input tokens $4.881 per M output tokens |
45170 neurons per M input tokens 443756 neurons per M output tokens |
| @cf/deepseek-ai/deepseek-v4-flash-0731 | $0.440 per M input tokens $0.014 per M cached input tokens $1.320 per M output tokens |
40000 neurons per M input tokens 1273 neurons per M cached input tokens 120000 neurons per M output tokens |
| @cf/deepseek-ai/deepseek-v4.1-flash-1017 | $0.300 per M input tokens $0.006 per M cached input tokens $1.200 per M output tokens |
27273 neurons per M input tokens 545 neurons per M cached input tokens 109091 neurons per M output tokens |
| @cf/deepseek-ai/deepseek-v4-pro-0813 | $1.320 per M input tokens $0.044 per M cached input tokens $3.960 per M output tokens |
120000 neurons per M input tokens 4000 neurons per M cached input tokens 360000 neurons per M output tokens |
| @cf/mistral/mistral-7b-instruct-v0.1 | $0.110 per M input tokens $0.190 per M output tokens |
10000 neurons per M input tokens 17300 neurons per M output tokens |
| @cf/mistralai/mistral-small-3.1-24b-instruct | $0.351 per M input tokens $0.555 per M output tokens |
31876 neurons per M input tokens 50488 neurons per M output tokens |
| @cf/meta/llama-3.1-8b-instruct | $0.282 per M input tokens $0.827 per M output tokens |
25608 neurons per M input tokens 75147 neurons per M output tokens |
| @cf/meta/llama-3.1-8b-instruct-fp8 | $0.152 per M input tokens $0.287 per M output tokens |
13778 neurons per M input tokens 26128 neurons per M output tokens |
| @cf/meta/llama-3.1-8b-instruct-awq | $0.123 per M input tokens $0.266 per M output tokens |
11161 neurons per M input tokens 24215 neurons per M output tokens |
| @cf/meta/llama-3-8b-instruct | $0.282 per M input tokens $0.827 per M output tokens |
25608 neurons per M input tokens 75147 neurons per M output tokens |
| @cf/meta/llama-3-8b-instruct-awq | $0.123 per M input tokens $0.266 per M output tokens |
11161 neurons per M input tokens 24215 neurons per M output tokens |
| @cf/meta/llama-2-7b-chat-fp16 | $0.556 per M input tokens $6.667 per M output tokens |
50505 neurons per M input tokens 606061 neurons per M output tokens |
| @cf/meta/llama-guard-3-8b | $0.484 per M input tokens $0.030 per M output tokens |
44003 neurons per M input tokens 2730 neurons per M output tokens |
| @cf/meta/llama-4-scout-17b-16e-instruct | $0.270 per M input tokens $0.850 per M output tokens |
24545 neurons per M input tokens 77273 neurons per M output tokens |
| @cf/google/gemma-3-12b-it | $0.345 per M input tokens $0.556 per M output tokens |
31371 neurons per M input tokens 50560 neurons per M output tokens |
| @cf/qwen/qwq-32b | $0.660 per M input tokens $1.000 per M output tokens |
60000 neurons per M input tokens 90909 neurons per M output tokens |
| @cf/qwen/qwen2.5-coder-32b-instruct | $0.660 per M input tokens $1.000 per M output tokens |
60000 neurons per M input tokens 90909 neurons per M output tokens |
| @cf/qwen/qwen3-30b-a3b-fp8 | $0.051 per M input tokens $0.335 per M output tokens |
4625 neurons per M input tokens 30475 neurons per M output tokens |
| @cf/qwen/qwen3.8-27b | $0.450 per M input tokens $3.200 per M output tokens |
40909 neurons per M input tokens 290909 neurons per M output tokens |
| @cf/openai/gpt-oss-120b | $0.350 per M input tokens $0.750 per M output tokens |
31818 neurons per M input tokens 68182 neurons per M output tokens |
| @cf/openai/gpt-oss-20b | $0.200 per M input tokens $0.300 per M output tokens |
18182 neurons per M input tokens 27273 neurons per M output tokens |
| @cf/aisingapore/gemma-sea-lion-v4-27b-it | $0.351 per M input tokens $0.555 per M output tokens |
31876 neurons per M input tokens 50488 neurons per M output tokens |
| @cf/ibm-granite/granite-4.0-h-micro | $0.017 per M input tokens $0.112 per M output tokens |
1542 neurons per M input tokens 10158 neurons per M output tokens |
| @cf/zai-org/glm-4.7-flash | $0.060 per M input tokens $0.400 per M output tokens |
5500 neurons per M input tokens 36400 neurons per M output tokens |
| @cf/zai-org/glm-5.2 | $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens |
127273 neurons per M input tokens 23636 neurons per M cached input tokens 400000 neurons per M output tokens |
| @cf/zai-org/glm-5.3 | $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens |
127273 neurons per M input tokens 23636 neurons per M cached input tokens 400000 neurons per M output tokens |
| @cf/zai-org/glm-5.3-flash | $0.150 per M input tokens $0.030 per M cached input tokens $0.500 per M output tokens |
13636 neurons per M input tokens 2727 neurons per M cached input tokens 45455 neurons per M output tokens |
| @cf/nvidia/nemotron-3-120b-a12b | $0.500 per M input tokens $1.500 per M output tokens |
45455 neurons per M input tokens 136364 neurons per M output tokens |
| @cf/moonshotai/kimi-k2.5 | $0.600 per M input tokens $0.100 per M cached input tokens $3.000 per M output tokens |
54545 neurons per M input tokens 9091 neurons per M cached input tokens 272727 neurons per M output tokens |
| @cf/moonshotai/kimi-k2.6 | $0.950 per M input tokens $0.160 per M cached input tokens $4.000 per M output tokens |
86364 neurons per M input tokens 14545 neurons per M cached input tokens 363636 neurons per M output tokens |
| @cf/moonshotai/kimi-k2.7-code | $0.950 per M input tokens $0.190 per M cached input tokens $4.000 per M output tokens |
86364 neurons per M input tokens 17273 neurons per M cached input tokens 363636 neurons per M output tokens |
| @cf/google/gemma-4-26b-a4b-it | $0.100 per M input tokens $0.300 per M output tokens |
9091 neurons per M input tokens 27273 neurons per M output tokens |
| @cf/daily-co/phonellm-mini-alpha-2 | $0.060 per M input tokens $0.240 per M output tokens |
5455 neurons per M input tokens 21818 neurons per M output tokens |
Embeddings model pricing
| Model | Price in Tokens | Price in Neurons |
|---|---|---|
| @cf/baai/bge-small-en-v1.5 | $0.020 per M input tokens | 1841 neurons per M input tokens |
| @cf/baai/bge-base-en-v1.5 | $0.067 per M input tokens | 6058 neurons per M input tokens |
| @cf/baai/bge-large-en-v1.5 | $0.204 per M input tokens | 18582 neurons per M input tokens |
| @cf/baai/bge-m3 | $0.012 per M input tokens | 1075 neurons per M input tokens |
| @cf/pfnet/plamo-embedding-1b | $0.019 per M input tokens | 1689 neurons per M input tokens |
| @cf/qwen/qwen3-embedding-0.6b | $0.012 per M input tokens | 1075 neurons per M input tokens |
Image model pricing
| Model | Price in Tokens | Price in Neurons |
|---|---|---|
| @cf/black-forest-labs/flux-1-schnell | $0.0000528 per 512x512 tile $0.0001056 per step |
4.80 neurons per 512x512 tile 9.60 neurons per step |
| @cf/leonardo/lucid-origin | $0.006996 per 512x512 tile $0.000132 per step |
636.00 neurons per 512x512 tile 12.00 neurons per step |
| @cf/leonardo/phoenix-1.0 | $0.005830 per 512x512 tile $0.000110 per step |
530.00 neurons per 512x512 tile 10.00 neurons per step |
| @cf/black-forest-labs/flux-2-dev | $0.00021 per input 512x512 tile, per step $0.00041 per output 512x512 tile, per step |
18.75 neurons per input 512x512 tile, per step 37.50 neurons per output 512x512 tile, per step |
| @cf/black-forest-labs/flux-2-klein-4b | $0.000059 per input 512x512 tile $0.000287 per output 512x512 tile |
5.37 neurons per input 512x512 tile 26.05 neurons per output 512x512 tile |
| @cf/black-forest-labs/flux-2-klein-9b | $0.015 per first MP (1024x1024) $0.002 per subsequent MP $0.002 per input image MP |
1363.64 neurons per first MP (1024x1024) 181.82 neurons per subsequent MP 181.82 neurons per input image MP |
Audio model pricing
| Model | Price in Tokens | Price in Neurons |
|---|---|---|
| @cf/openai/whisper | $0.0005 per audio minute | 41.14 neurons per audio minute |
| @cf/openai/whisper-large-v3-turbo | $0.0005 per audio minute | 46.63 neurons per audio minute |
| @cf/myshell-ai/melotts | $0.0002 per audio minute | 18.63 neurons per audio minute |
| @cf/deepgram/aura-1 | $0.015 per 1k characters input |
1,363.64 neurons per 1k characters input |
| @cf/deepgram/nova-3 | $0.0052 per audio minute input |
472.73 neurons per audio minute input |
| @cf/deepgram/nova-3 (WebSocket) | $0.0092 per audio minute input |
836.36 neurons per audio minute input |
| @cf/pipecat-ai/smart-turn-v2 | $0.00033795 per audio minute input |
0.51 neurons per audio minute input |
| @cf/deepgram/aura-2-en | $0.030 per 1k characters input |
2727.27 neurons per 1k characters input |
| @cf/deepgram/aura-2-es | $0.030 per 1k characters input |
2727.27 neurons per 1k characters input |
| @cf/deepgram/flux (WebSocket) | $0.0077 per audio minute |
700.00 neurons per audio minute |
Other model pricing
| Model | Price in Tokens | Price in Neurons |
|---|---|---|
| @cf/huggingface/distilbert-sst-2-int8 | $0.026 per M input tokens | 2394 neurons per M input tokens |
| @cf/baai/bge-reranker-base | $0.003 per M input tokens | 283 neurons per M input tokens |
| @cf/meta/m2m100-1.2b | $0.342 per M input tokens $0.342 per M output tokens |
31050 neurons per M input tokens 31050 neurons per M output tokens |
| @cf/microsoft/resnet-50 | $2.51 per M images | 228055 neurons per M images |
| @cf/ai4bharat/indictrans2-en-indic-1B | $0.342 per M input tokens $0.342 per M output tokens |
31050 neurons per M input tokens 31050 neurons per M output tokens |
| @cf/moondream/moondream3.1-9B-A2B | $0.300 per M input tokens $1.000 per M output tokens |
27273 neurons per M input tokens 90909 neurons per M output tokens |
| @cf/cloudflare/clef | $0.240 per M input tokens | 21818 neurons per M input tokens |
| @cf/cloudflare/clef-omni | $0.150 per M input tokens | 13636 neurons per M input tokens |
| @cf/cloudflare/clef-flash | $0.038 per M input tokens | 3455 neurons per M input tokens |
| @cf/cloudflare/clairic | $0.100 per M input tokens | 9091 neurons per M input tokens |
Limits
As of Nov 3, 2026, from Cloudflare's docs, last updated there Sep 17, 2026. Licensed CC BY 4.0; navigation removed.
Workers AI is now Generally Available. We've updated our rate limits to reflect this.
Note that model inferences in local mode using Wrangler will also count towards these limits. Beta models may have lower rate limits while we work on performance and scale.
Custom requirements
If you have custom requirements like private custom models or higher limits, complete the Custom Requirements Form ↗︎. Cloudflare will contact you with next steps.
Rate limits are default per task type, with some per-model limits defined as follows:
Rate limits by task type
Automatic Speech Recognition
- 720 requests per minute
Image Classification
- 3000 requests per minute
Image-to-Text
- 720 requests per minute
Object Detection
- 3000 requests per minute
Summarization
- 1500 requests per minute
Text Classification
- 2000 requests per minute
Text Embeddings
- 3000 requests per minute
- @cf/baai/bge-large-en-v1.5 is 1500 requests per minute
Text Generation
- 300 requests per minute, unless the model requires the Workers Paid plan
Paid models
The following limits apply per account, per model to any model that requires the Workers Paid plan — each model page states whether it does. These models are the only models that do not receive the default limit:
| Billing | Rate limit |
|---|---|
| Standard Workers AI billing | 20 requests per minute |
| Prepaid AI Gateway credits | 50 requests per minute |
To receive the elevated limit, load prepaid AI Gateway credits and set the gateway's Workers AI billing setting to Unified billing. These limits are designed for typical agentic and coding workloads, where requests to frontier models can take longer to complete.
Text-to-Image
- 720 requests per minute
- @cf/runwayml/stable-diffusion-v1-5-img2img is 1500 requests per minute
Translation
- 720 requests per minute
Timeline
October 2026
- Cross-request KV cache exposure in the GLM-5.3 Workers AI model, and our remediation with SGLang Blog
A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests. Here is how we addressed the issue.
- createAI replaces workers-ai-provider and ai-gateway-provider
The Agents SDK has a new createAI function for the AI SDK and Pi AI. It unifies what workers-ai-provider and ai-gateway-provider did: Workers AI models, AI Gateway catalog models, dynamic routes, and vendor models, through the AI binding or an account id and API token. workers-ai-provider and ai-gateway-provider are now feature frozen and marked as deprecated. Please migrate at your convenience.…
- Introducing Clairic, a new System One class of extraction models Blog
Clairic is a new model from Cloudflare that is a System One extraction modeI, capable of extracting, computing, estimating, and forecasting data from unstructured inputs.
- Introducing Clairic: an extraction model for typed values, now on Workers AI
@cf/cloudflare/clairic is now available on Workers AI as a preview. Clairic is the first extraction model: a System One model that answers with values instead of text. We intend to release the model with open weights soon. Decision models such as Clef choose among options you define up front. Many structured-output tasks do not have answers you can list in advance: an invoice total, a delivery da…
- DeepSeek V4.1 Flash 1017 now available on Workers AI
@cf/deepseek-ai/deepseek-v4.1-flash-1017 is now available on Workers AI. DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters. It activates 8B parameters per token during prefill and 16B during decode, which keeps input-heavy agentic workloads fast and low-cost. The 1017 release is an update to DeepSeek V4.1 Flash with improvements across reasoning, coding, a…
- Pipecat PhoneLLM Mini now available on Workers AI
@cf/daily-co/phonellm-mini-alpha-2, a model from the Pipecat ↗︎ team at Daily, is now available on Workers AI. PhoneLLM is built for voice agents and other realtime AI applications, where a model has to reply quickly and call the right tool mid-conversation. In a voice agent, the language model sits between speech-to-text and text-to-speech, so every second it takes adds to the caller's wait. Dev…
- Clef-omni adds audio and video input, Clef-flash is now cheaper, and Clef is faster
@cf/cloudflare/clef-omni is now available on Workers AI. Clef-omni is a decision model that takes audio (WAV or MP3) and video (MP4 or WebM) input alongside text and images. It joins Clef and Clef-flash in the Clef family of open-weight decision models. We also cut the price of Clef-flash, so it now costs less than Jev, and made Clef faster. Clef-omni: one decision model for every modality Previo…
- Introducing Clef: Cloudflare's first open-source decision models, now on Workers AI
Meet @cf/cloudflare/clef and @cf/cloudflare/clef-flash, the first models trained by the Cloudflare Workers AI team, available on Workers AI today. Clef is a decision model, in the same family as Typesafe's Jev ↗︎. Instead of generating text, it reads an input state and a set of typed questions, then returns a probability for every allowed answer. Your agent gets a structured decision it can act o…
September 2026
- Reject busy synchronous inference requests
The rejectIfBusy option lets synchronous Workers AI inference requests fail when capacity is unavailable. Use it when your application should not wait in a capacity queue. Pass the option as the third argument to the Workers AI binding: const response = await env.AI.run( "@cf/google/gemma-4-26b-a4b-it", { messages: [{ role: "user", content: "Explain capacity queues." }], }, { rejectIfBusy: true }…
August 2026
- Z.ai GLM-5.3 now available on Workers AI
@cf/zai-org/glm-5.3 is now available on Workers AI. It is Z.ai's flagship agentic coding model, built for long-running, tool-driven development workflows rather than single-turn chat. GLM-5.3 uses the same base model as GLM-5.2, with every gain coming from post-training. The results are substantial on coding and agentic benchmarks: Z.ai reports ↗︎ a 50% improvement over GLM-5.2 on its in-house Z.…
- Z.ai GLM-5.3 Flash now available on Workers AI
@cf/zai-org/glm-5.3-flash is now available on Workers AI. It is the first natively multimodal model in the GLM-5 series, built on a Mixture-of-Experts architecture with 320B total parameters and 18B active per token. GLM-5.3 Flash is the first GLM-family model on Workers AI to support multimodal inputs. It outperforms GLM-5.2 across benchmarks and real-world workloads at a lower price, while appr…
- Qwen 3.8 27B now available on Workers AI
@cf/qwen/qwen3.8-27b is now available on Workers AI. Qwen 3.8 27B is a 27-billion-parameter instruction-tuned vision language model from Alibaba's Qwen family. It processes images and text together, with reasoning and function calling for agentic workflows. Key capabilities: Vision: Accept image and text inputs and generate text responses. Reasoning: Support thinking mode for complex, step-by-ste…
- DeepSeek V4 Flash and Pro now available on Workers AI
@cf/deepseek-ai/deepseek-v4-pro-0813 and @cf/deepseek-ai/deepseek-v4-flash-0731 are now available on Workers AI. DeepSeek V4 Flash and DeepSeek V4 Pro are the first Workers AI models with a full one million (1,048,576) token context window. Use them for long-horizon agentic workflows, large codebases, and multi-step reasoning that exceed the context limits of every other model hosted on the platf…
- Workers AI and AI Gateway unify model access and billing
Workers AI and AI Gateway now provide a unified path for accessing models and managing inference traffic. Use the same AI binding and REST API to call models hosted on Workers AI or by supported third-party providers, with AI Gateway providing observability, logging, caching, security, and billing controls. Unified entrypoints and observability The AI binding supports both Workers AI and third-pa…
July 2026
- Select models now require the Workers Paid plan
We are limiting Workers Free plan access to a few resource-intensive models so we can prioritize capacity for the broader Workers AI user base. This helps everyone get a more reliable inference experience, with fewer 429 and 3040 (Out of Capacity) errors. The following models now require the Workers Paid plan: @cf/moonshotai/kimi-k2.6 @cf/moonshotai/kimi-k2.7-code @cf/zai-org/glm-5.2 On the Worke…
- Plain text output for Markdown Conversion
The Markdown Conversion service now supports a new output conversion option that controls the format of the converted content. Set output.format to text to receive plain text with Markdown syntax removed. The default value is markdown, so existing conversions are unchanged. Use the env.AI binding: await env.AI.toMarkdown( { name: "page.html", blob: new Blob([html]) }, { conversionOptions: { outpu…
- Workers AI toMarkdown and AI Search now supports GIF and BMP image conversion
Workers AI Markdown conversion (toMarkdown) now supports .gif and .bmp image files, in addition to the JPEG, PNG, WebP, and SVG formats already supported. GIF and BMP files run through the same image pipeline as other formats. Each image is resized if needed (and for animated GIFs, only the first frame is used), then passed to an object-detection model to identify what it contains. Those detected…
- Moondream 3.1 now available on Workers AI
Partnering with Moondream ↗︎ to bring their latest model @cf/moondream/moondream3.1-9B-A2B to Workers AI. Moondream 3.1 is a fast vision language model built on a mixture-of-experts architecture with 9B total parameters and 2B active, delivering frontier-level visual reasoning while retaining fast, cost-efficient inference. Moondream 3.1 is designed for real-world vision tasks, with a 32K token c…
June 2026
- Introducing GLM-5.2 on Workers AI
We are excited to announce GLM-5.2 on Workers AI, Z.ai's flagship agentic coding model. @cf/zai-org/glm-5.2 is a text generation model built for agentic coding workflows. With function calling and reasoning support, it can handle long codebases, multi-step planning, and tool-augmented agents. Key features and use cases: Agentic coding: Designed for autonomous coding tasks, long-horizon planning,…
- Moonshot AI Kimi K2.7 Code now available on Workers AI
@cf/moonshotai/kimi-k2.7-code is now available on Workers AI. Kimi K2.7 Code is a code-optimized variant of the Kimi K2 family, built on a Mixture-of-Experts architecture with 1T total parameters and 32B active per token. Improved coding and agent performance K2.7 Code delivers meaningful gains over K2.6 on coding and agentic benchmarks: +21.8% on Kimi Code Bench v2 +11.0% on Program Bench +31.5%…
May 2026
- Planned model deprecations on Workers AI
We are refreshing the Workers AI model catalog to make room for newer releases. Please update your apps to remove references to the models listed below before the deprecation date. Recommended replacements @cf/zai-org/glm-4.7-flash — fast multilingual model with multi-turn tool calling and coding capabilities. @cf/google/gemma-4-26b-a4b-it — efficient open model with vision and tool calling. @cf/…
April 2026
- Moonshot AI Kimi K2.6 now available on Workers AI
@cf/moonshotai/kimi-k2.6 is now available on Workers AI, in partnership with Moonshot AI for Day 0 support. Kimi K2.6 is a native multimodal agentic model from Moonshot AI that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration. Built on a Mixture-of-Experts architecture with 1T total parameters and 32B…
- Google Gemma 4 26B A4B now available on Workers AI
We are partnering with Google to bring @cf/google/gemma-4-26b-a4b-it to Workers AI. Gemma 4 26B A4B is a Mixture-of-Experts (MoE) model built from Gemini 3 research, with 26B total parameters and only 4B active per forward pass. By activating a small subset of parameters during inference, the model runs almost as fast as a 4B-parameter model while delivering the quality of a much larger one. Gemm…
March 2026
- Moonshot AI Kimi K2.5 now available on Workers AI
Workers AI is officially in the big models game. @cf/moonshotai/kimi-k2.5 is the first frontier-scale open-source model on our AI inference platform — a large model with a full 256k context window, multi-turn tool calling, vision inputs, and structured outputs. By bringing a frontier-scale model directly onto the Cloudflare Developer Platform, you can now run the entire agent lifecycle on a singl…
- NVIDIA Nemotron 3 Super now available on Workers AI
We're excited to partner with NVIDIA to bring @cf/nvidia/nemotron-3-120b-a12b to Workers AI. NVIDIA Nemotron 3 Super is a Mixture-of-Experts (MoE) model with a hybrid Mamba-transformer architecture, 120B total parameters, and 12B active parameters per forward pass. The model is optimized for running many collaborating agents per application. It delivers high accuracy for reasoning, tool calling,…
- Real-time transcription in RealtimeKit now supports 10 languages with regional variants
Real-time transcription in RealtimeKit now supports 10 languages with regional variants, powered by Deepgram Nova-3 running on Workers AI. During a meeting, participant audio is routed through AI Gateway to Nova-3 on Workers AI — so transcription runs on Cloudflare's network end-to-end, reducing latency compared to routing through external speech-to-text services. Set the language when creating a…
- New conversion options for Markdown Conversion
You can now customize how the Markdown Conversion service processes different file types by passing a conversionOptions object. Available options: Images: Set the language for AI-generated image descriptions HTML: Use CSS selectors to extract specific content, or provide a hostname to resolve relative links PDF: Exclude metadata from the output Use the env.AI binding: await env.AI.toMarkdown( { n…
February 2026
- AI dashboard experience improvements
Workers AI and AI Gateway have received a series of dashboard improvements to help you get started faster and manage your AI workloads more easily. Navigation and discoverability AI now has its own top-level section in the Cloudflare dashboard sidebar, so you can find AI features without digging through menus. The new top-level AI section in the dashboard sidebar. Onboarding and getting started G…
- Introducing GLM-4.7-Flash on Workers AI, @cloudflare/tanstack-ai, and workers-ai-provider v3.1.1
We're excited to announce GLM-4.7-Flash on Workers AI, a fast and efficient text generation model optimized for multilingual dialogue and instruction-following tasks, along with the brand-new @cloudflare/tanstack-ai ↗︎ package and workers-ai-provider v3.1.1 ↗︎. You can now run AI agents entirely on Cloudflare. With GLM-4.7-Flash's multi-turn tool calling support, plus full compatibility with TanS…
January 2026
- Launching FLUX.2 [klein] 9B on Workers AI
We have partnered with Black Forest Labs (BFL) again to bring their optimized FLUX.2 [klein] 9B model to Workers AI. This distilled model offers enhanced quality compared to the 4B variant, while maintaining cost-effective pricing. With a fixed 4-step inference process, Klein 9B is ideal for rapid prototyping and real-time applications where both speed and quality matter. Read the BFL blog ↗︎ to…
- Launching FLUX.2 [klein] 4B on Workers AI
We've partnered with Black Forest Labs (BFL) again to bring their optimized FLUX.2 [klein] 4B model to Workers AI! This distilled model offers faster generation and cost-effective pricing, while maintaining great output quality. With a fixed 4-step inference process, Klein 4B is ideal for rapid prototyping and real-time applications where speed matters. Read the BFL blog ↗︎ to learn more about th…
November 2025
- Launching FLUX.2 [dev] on Workers AI
We've partnered with Black Forest Labs (BFL) to bring their latest FLUX.2 [dev] model to Workers AI! This model excels in generating high-fidelity images with physical world grounding, multi-language support, and digital asset creation. You can also create specific super images with granular controls like JSON prompting. Read the BFL blog ↗︎ to learn more about the model itself. Read our Cloudfla…
October 2025
- Workers AI Markdown Conversion: New endpoint to list supported formats
Developers can now programmatically retrieve a list of all file formats supported by the Markdown Conversion utility in Workers AI. You can use the env.AI binding: await env.AI.toMarkdown().supported() Or call the REST API: curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/tomarkdown/supported \ -H 'Authorization: Bearer {API_TOKEN}' Both return a list of file formats that users…
- New Deepgram Flux model available on Workers AI
Deepgram's newest Flux model @cf/deepgram/flux is now available on Workers AI, hosted directly on Cloudflare's infrastructure. We're excited to be a launch partner with Deepgram and offer their new Speech Recognition model built specifically for enabling voice agents. Check out Deepgram's blog ↗︎ for more details on the release. The Flux model can be used in conjunction with Deepgram's speech-to-…
September 2025
- Introducing EmbeddingGemma from Google on Workers AI
We're excited to be a launch partner alongside Google ↗︎ to bring their newest embedding model, EmbeddingGemma, to Workers AI that delivers best-in-class performance for its size, enabling RAG and semantic search use cases. @cf/google/embeddinggemma-300m is a 300M parameter embedding model from Google, built from Gemma 3 and the same research used to create Gemini models. This multilingual model…
August 2025
- Deepgram and Leonardo partner models now available on Workers AI
New state-of-the-art models have landed on Workers AI! This time, we're introducing new partner models trained by our friends at Deepgram ↗︎ and Leonardo ↗︎, hosted on Workers AI infrastructure. As well, we're introuding a new turn detection model that enables you to detect when someone is done speaking — useful for building voice agents! Read the blog ↗︎ for more details and check out some of th…
- OpenAI open models now available on Workers AI
We're thrilled to be a Day 0 partner with OpenAI ↗︎ to bring their latest open models ↗︎ to Workers AI, including support for Responses API, Code Interpreter, and Web Search (coming soon). Get started with the new models at @cf/openai/gpt-oss-120b and @cf/openai/gpt-oss-20b. Check out the blog ↗︎ for more details about the new models, and the gpt-oss-120b and gpt-oss-20b model pages for more info…
April 2025
- Workers AI for Developer Week - faster inference, new models, async batch API, expanded LoRA support
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. Faster inference + New models 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…
March 2025
- Markdown conversion in Workers AI
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 endpoi…
- New models in Workers AI
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.…
February 2025
- Workers AI now supports structured JSON outputs.
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…
- Workers AI larger context windows
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…
- Workers AI updated pricing
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 fle…