The existing ai models in this project are being depreciated

[kaniamutan14]

I received mail saying the current AI models which are being used in this project is being depreciated kimi is being aliased so no problem but lama-3.1-8b-instruct is being depreciated

Hi Workers AI users,



We are planning to deprecate some of the older models in the Workers AI catalog. We refresh our model catalog to make room for new releases and updated models. Please update your apps and remove references to the older models.



We recommend you use our newer models such as a fast tool-calling model like GLM 4.7 Flash and Gemma 4, or a capable tool-calling and vision model like Kimi K2.6. The Kimi K2.5 model will be aliased to K2.6 on May 10th, so your apps using K2.5 will keep working, but will be served by K2.6 ([model and pricing details here](https://links1.cloudflare.com/s/c/KWtATSd498truZO0KQf4MPnhVbvStH8Dzr_w-mwvuFMv5SftKVL0UkZ0WFPnKYNsngPpe7Cpg_Cq5e2kFRaN7f_mlBnpoSoWv2NtN14vbR1pyMENYXzELMVqUC_tz9cinI3A1MRysZntZqjztnVN8__0TltCQ7dHsZTKNImcIU8Rv6Skrs726k0YxQ0mhVGq5adHHkajbB8nTZ0XSh22pB72ZY3vUhqD0PeFHSoWs85MB10wmrzfvFhWhEljRDT0MoQFYiBuG8pIWG0v3P0GNNcYrJ1HfnH_rB0D8r8FMBpBRAPRfHKp47RcxenAT5OOeJtsp7xvvaZzuziVDcY4VLVIG00-omGlJZjTMJbcwLM3jtpXOktFkyXTcriaMkx-sVjTUKssQi1kSYudsrm9NmZtywrOxyaspSf2nj4yC5j_OxrrrVbLrSaxuoxWlhDR6KS2fpZjdFGugK0/KZVYlBX3A3cbohgAiOOEesTreJ5Jen9H/20)). The rest of the following models will be deprecated on May 30th, 2026: 



Models planned for deprecation and newer models:

@cf/moonshotai/kimi-k2.5 → @cf/moonshotai/kimi-k2.6 (May 10th)

@hf/meta-llama/meta-llama-3-8b-instruct

@cf/meta/llama-3-8b-instruct

@cf/meta/llama-3-8b-instruct-awq

@cf/meta/llama-3.1-8b-instruct

@cf/meta/llama-3.1-8b-instruct-awq

@cf/meta/llama-3.1-70b-instruct

@cf/meta/llama-2-7b-chat-int8

@cf/meta/llama-2-7b-chat-fp16

@cf/mistral/mistral-7b-instruct-v0.1

@hf/google/gemma-7b-it

@cf/google/gemma-3-12b-it

@hf/nousresearch/hermes-2-pro-mistral-7b

@cf/microsoft/phi-2

@cf/defog/sqlcoder-7b-2

@cf/unum/uform-gen2-qwen-500m

@cf/facebook/bart-large-cnn

@hf/mistral/mistral-7b-instruct-v0.2



Thanks for building with us!