Cloudflare Workers AI deprecates 24 models on November 15
16 LLMs leave on November 15, including DeepSeek V4 Pro 0813, Kimi K2.6 and GLM 5.3 Flash.
Cloudflare said on November 5, 2026 that it will deprecate 24 models on Workers AI on November 15, 2026, and asked developers to remove references to them from their apps before that date. The list covers 16 LLMs, including DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, Kimi K2.6, Kimi K2.7 Code, GLM 5.2 and GLM 5.3 Flash, plus 8 image, speech, vision and embedding models.
What changed
- 16 LLMs deprecated on November 15:
@cf/deepseek-ai/deepseek-v4-pro-0813,@cf/deepseek-ai/deepseek-v4-flash-0731,@cf/deepseek-ai/deepseek-r1-distill-qwen-32b,@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/nvidia/nemotron-3-120b-a12b,@cf/qwen/qwq-32b,@cf/qwen/qwen3-30b-a3b-fp8,@cf/meta/llama-3.1-8b-instruct-fp8,@cf/meta/llama-3.2-1b-instruct,@cf/meta/llama-3.2-3b-instructand three LoRA base models (@cf/meta-llama/llama-2-7b-chat-hf-lora,@cf/google/gemma-2b-it-lora,@cf/google/gemma-7b-it-lora). - Cloudflare names no one-to-one replacement for the LLMs. It recommends newer models in general.
- The 8 other models get named replacements, for example
@cf/openai/whisper-tiny-ento@cf/deepgram/nova-3and four Stable Diffusion variants to@cf/black-forest-labs/flux-2-klein-9b. - Cloudflare says it is refreshing the Workers AI catalog "to make room for new releases and updated models."
Where the same models run on RouterPlus
RouterPlus does not route any of these models through Workers AI. Eight of the deprecated LLMs are in the RouterPlus catalog from other hosts. Prices per million tokens from the RouterPlus catalog on November 6, 2026, opt-in hosts excluded:
| Model | Hosts | Lowest input | Lowest output |
|---|---|---|---|
| DeepSeek V4 Pro 0813 | 6 | $0.92 | $2.60 |
| DeepSeek V4 Flash 0731 | 8 | $0.06 | $0.18 |
| Kimi K2.6 | 4 | $0.39 | $1.80 |
| GLM 5.2 | 8 | $0.19 | $1.80 |
| GLM 5.3 Flash | 11 | $0.05 | $0.20 |
| Qwen3 30B A3B | 1 | $0.12 | $0.50 |
| Llama 3.2 1B Instruct | 1 | $0.027 | $0.201 |
| Llama 3.2 3B Instruct | 1 | $0.05 | $0.33 |
Model pages: DeepSeek V4 Pro 0813, DeepSeek V4 Flash 0731, Kimi K2.6, GLM 5.2, GLM 5.3 Flash, Qwen3 30B A3B.
What to do
Swap the Workers AI model ID for the RouterPlus catalog ID and point the request at api.routerplus.com:
@cf/deepseek-ai/deepseek-v4-pro-0813 -> deepseek/deepseek-v4-pro-0813
@cf/zai-org/glm-5.3-flash -> z-ai/glm-5.3-flash
@cf/moonshotai/kimi-k2.6 -> moonshotai/kimi-k2.6curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek/deepseek-v4-pro-0813", "messages": [{"role": "user", "content": "Hello"}]}'Sign up at app.routerplus.com/login for an API key. Kimi K2.7 Code, Nemotron 3 120B A12B, QwQ 32B, R1 Distill Qwen 32B and Llama 3.1 8B are not in the RouterPlus catalog as of November 6, 2026.
