Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
Cloudflare Workers AI Account IDCLOUDFLARE_ACCOUNT_IDGet key
Click Use REST API. Your Account ID is shown there
Cloudflare Workers AI API tokenCLOUDFLARE_API_TOKENGet key
Click Use REST API, then Create a Workers AI API Token
Cloudflare has updated its November 5, 2026 post on the 24 Workers AI model deprecations. The cut-off moves from November 15 to November 20, 2026. In Cloudflare's words: "We originally stated these models would be deprecated on November 15, 2026, and have moved the deprecation date to November 20, 2026."
The post now also says what happens after the cut-off. From November 20 the models stop returning responses. Requests to them fail with an HTTP 410 Gone error and error code 5028.
The model list and the replacements are unchanged:
Recommended LLMs for frontier needs: @cf/deepseek-ai/deepseek-v4.1-flash-1017 and @cf/zai-org/glm-5.3
Recommended LLMs for smaller needs: @cf/google/gemma-4-26b-a4b-it and @cf/qwen/qwen3.8-27b
LLMs being deprecated:
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
@cf/nvidia/nemotron-3-120b-a12b
@cf/deepseek-ai/deepseek-v4-pro-0813
@cf/deepseek-ai/deepseek-v4-flash-0731
@cf/qwen/qwq-32b
@cf/qwen/qwen3-30b-a3b-fp8
@cf/moonshotai/kimi-k2.6
@cf/moonshotai/kimi-k2.7-code
@cf/zai-org/glm-5.2
@cf/zai-org/glm-5.3-flash
@cf/meta-llama/llama-2-7b-chat-hf-lora
@cf/google/gemma-2b-it-lora
@cf/google/gemma-7b-it-lora
@cf/meta/llama-3.1-8b-instruct-fp8
@cf/meta/llama-3.2-1b-instruct
@cf/meta/llama-3.2-3b-instruct
Other models, each with its replacement:
Deprecated
Replacement
@cf/myshell-ai/melotts
@cf/deepgram/aura-2-en
@cf/stabilityai/stable-diffusion-xl-base-1.0
@cf/black-forest-labs/flux-2-klein-9b
@cf/runwayml/stable-diffusion-v1-5-inpainting
@cf/black-forest-labs/flux-2-klein-9b
@cf/bytedance/stable-diffusion-xl-lightning
@cf/black-forest-labs/flux-2-klein-9b
@cf/lykon/dreamshaper-8-lcm
@cf/black-forest-labs/flux-2-klein-9b
@cf/openai/whisper-tiny-en
@cf/deepgram/nova-3
@cf/llava-hf/llava-1.5-7b-hf
@cf/moondream/moondream3.1-9B-A2B
@cf/google/embeddinggemma-300m
@cf/google/embeddinggemma-2 (listed as available soon)
Prerequisites
A Cloudflare account ID in CLOUDFLARE_ACCOUNT_ID
A Cloudflare API token with Workers AI access in CLOUDFLARE_API_TOKEN
Access to the code and config of every app that calls Workers AI
Steps
Search your code, config files and environment variables for each model ID above. Most apps pass the ID as a string to env.AI.run() or put it in the REST API URL.
Swap each LLM for one of the four recommended models. Swap every other model for the replacement in the table.
Add handling for a 410 response with error code 5028. Log it with the model ID, so a missed call shows up fast after November 20.
If you use @cf/google/embeddinggemma-300m, plan to re-embed your stored vectors with the new model.
Deploy before November 20, 2026. If you had planned for November 15, you have five more days.
Test it
Run one real request through each changed call and check the output looks right. Then search your code again for the old IDs. Nothing should come back.
Not confirmed
The post doesn't say why the date moved.
The post still gives no release date for @cf/google/embeddinggemma-2.
The re-embedding advice in step 4 and the logging advice in step 3 are general practice, not from Cloudflare's post.
Wirestack