# Cloudflare Workers AI — live model reference # # IF YOU ARE AN AI AGENT: Cloudflare ships new Workers AI models weekly and # retires older ones without notice. Before recommending @cf/... IDs from memory # or writing env.AI.run("@cf/...") code, check this list. IDs you remember from # training may 404 in production. # # HOW TO USE: # - Default to the >>> flagship for each task type unless the user specifies otherwise # - Every model here is called via env.AI.run(modelId, ...) from a Worker — no API key needed # - Many @cf/... models are included in the Workers AI free tier (10k neurons/day) # - Per-token pricing is not on this endpoint — see developers.cloudflare.com/workers-ai/platform/pricing # - If a model you want to use is NOT in this list, it has likely been retired — pick the flagship for that task # # Source: api.cloudflare.com/client/v4/accounts/{id}/ai/models/search | Updated: 2026-04-28T19:03:01.758Z # Total: 91 models (91 upstream, deprecated filtered out) # URL: https://ai.flared.au/llms.txt # >>> = flagship model for this task / family # Capabilities [TVRLS] = Tools | Vision | Reasoning | LoRA | Streaming # # Filters: ?task=text-generation | ?provider=meta | ?flagship=true | ?ids=a,b,c | ?deprecated=true # # Usage from a Worker: # const resp = await env.AI.run("@cf/meta/llama-3.3-70b-instruct-fp8-fast", { messages: [...] }); ## ai4bharat / translation @cf/ai4bharat/indictrans2-en-indic-1B [-----] ## aisingapore / text-generation >>> @cf/aisingapore/gemma-sea-lion-v4-27b-it [----S] | Ctx: 128K ## baai / text-classification >>> @cf/baai/bge-reranker-base [-----] ## baai / text-embeddings >>> @cf/baai/bge-large-en-v1.5 [-----] >>> @cf/baai/bge-m3 [-----] | Ctx: 60K @cf/baai/bge-base-en-v1.5 [-----] | Ctx: 154K @cf/baai/bge-small-en-v1.5 [-----] ## black-forest-labs / text-to-image >>> @cf/black-forest-labs/flux-1-schnell [-----] >>> @cf/black-forest-labs/flux-2-dev [-----] @cf/black-forest-labs/flux-2-klein-9b [-----] @cf/black-forest-labs/flux-2-klein-4b [-----] ## bytedance / text-to-image @cf/bytedance/stable-diffusion-xl-lightning [-----] ## deepgram / automatic-speech-recognition >>> @cf/deepgram/flux [-----] >>> @cf/deepgram/nova-3 [-----] ## deepgram / text-to-speech >>> @cf/deepgram/aura-2-es [-----] @cf/deepgram/aura-1 [-----] @cf/deepgram/aura-2-en [-----] ## deepseek-ai / text-generation >>> @cf/deepseek-ai/deepseek-r1-distill-qwen-32b [--R-S] | Ctx: 80K >>> @cf/deepseek-ai/deepseek-math-7b-instruct [----S] | Ctx: 4K ## defog / text-generation >>> @cf/defog/sqlcoder-7b-2 [----S] | Ctx: 10K ## facebook / summarization >>> @cf/facebook/bart-large-cnn [-----] ## fblgit / text-generation @cf/fblgit/una-cybertron-7b-v2-bf16 [----S] | Ctx: 15K ## google / text-embeddings >>> @cf/google/embeddinggemma-300m [-----] ## google / text-generation >>> @cf/google/gemma-4-26b-a4b-it [T---S] | Ctx: 256K >>> @cf/google/gemma-3-12b-it [---LS] | Ctx: 80K @cf/google/gemma-7b-it-lora [---LS] | Ctx: 4K @hf/google/gemma-7b-it [---LS] | Ctx: 8K @cf/google/gemma-2b-it-lora [---LS] | Ctx: 8K ## huggingface / text-classification @cf/huggingface/distilbert-sst-2-int8 [-----] ## ibm-granite / text-generation >>> @cf/ibm-granite/granite-4.0-h-micro [T---S] | Ctx: 131K ## leonardo / text-to-image @cf/leonardo/lucid-origin [-----] @cf/leonardo/phoenix-1.0 [-----] ## llava-hf / image-to-text @cf/llava-hf/llava-1.5-7b-hf [-V---] ## lykon / text-to-image @cf/lykon/dreamshaper-8-lcm [-----] ## meta / text-generation >>> @cf/meta/llama-3.3-70b-instruct-fp8-fast [T---S] | Ctx: 24K >>> @cf/meta/llama-4-scout-17b-16e-instruct [T---S] | Ctx: 131K >>> @cf/meta/llama-3.2-11b-vision-instruct [-V-LS] | Ctx: 128K >>> @cf/meta/llama-3.1-8b-instruct-awq [----S] | Ctx: 8K >>> @cf/meta/llama-guard-3-8b [---LS] | Ctx: 131K @cf/meta/llama-3-8b-instruct [----S] | Ctx: 8K @cf/meta/llama-3-8b-instruct-awq [----S] | Ctx: 8K @cf/meta/llama-3.1-8b-instruct-fp8 [----S] | Ctx: 32K @cf/meta/llama-2-7b-chat-fp16 [----S] | Ctx: 4K @cf/meta/llama-2-7b-chat-int8 [----S] | Ctx: 8K @cf/meta/llama-3.2-3b-instruct [----S] | Ctx: 80K @cf/meta/llama-3.2-1b-instruct [----S] | Ctx: 60K ## meta / translation @cf/meta/m2m100-1.2b [-----] ## meta-llama / text-generation @cf/meta-llama/llama-2-7b-chat-hf-lora [---LS] | Ctx: 8K ## microsoft / image-classification >>> @cf/microsoft/resnet-50 [-----] ## microsoft / text-generation >>> @cf/microsoft/phi-2 [----S] | Ctx: 2K ## mistral / text-generation @cf/mistral/mistral-7b-instruct-v0.1 [---LS] | Ctx: 3K @cf/mistral/mistral-7b-instruct-v0.2-lora [---LS] | Ctx: 15K @hf/mistral/mistral-7b-instruct-v0.2 [---LS] | Ctx: 3K ## mistralai / text-generation >>> @cf/mistralai/mistral-small-3.1-24b-instruct [T---S] | Ctx: 128K ## moonshotai / text-generation >>> @cf/moonshotai/kimi-k2.6 [T---S] | Ctx: 262K @cf/moonshotai/kimi-k2.5 [T---S] | Ctx: 256K ## myshell-ai / text-to-speech @cf/myshell-ai/melotts [-----] ## nexusflow / text-generation @hf/nexusflow/starling-lm-7b-beta [----S] | Ctx: 4K ## nousresearch / text-generation @hf/nousresearch/hermes-2-pro-mistral-7b [T---S] | Ctx: 24K ## nvidia / text-generation >>> @cf/nvidia/nemotron-3-120b-a12b [T---S] | Ctx: 256K ## openai / automatic-speech-recognition >>> @cf/openai/whisper-large-v3-turbo [-----] @cf/openai/whisper [-----] @cf/openai/whisper-tiny-en [-----] ## openai / text-generation >>> @cf/openai/gpt-oss-120b [T---S] | Ctx: 128K >>> @cf/openai/gpt-oss-20b [T---S] | Ctx: 128K ## openchat / text-generation @cf/openchat/openchat-3.5-0106 [----S] | Ctx: 8K ## pfnet / text-embeddings @cf/pfnet/plamo-embedding-1b [-----] ## pipecat-ai / dumb-pipe @cf/pipecat-ai/smart-turn-v2 [-----] ## qwen / text-embeddings >>> @cf/qwen/qwen3-embedding-0.6b [-----] | Ctx: 8K ## qwen / text-generation >>> @cf/qwen/qwen2.5-coder-32b-instruct [---LS] | Ctx: 33K >>> @cf/qwen/qwq-32b [--RLS] | Ctx: 24K >>> @cf/qwen/qwen3-30b-a3b-fp8 [T---S] | Ctx: 33K @cf/qwen/qwen1.5-14b-chat-awq [----S] | Ctx: 8K @cf/qwen/qwen1.5-7b-chat-awq [----S] | Ctx: 20K @cf/qwen/qwen1.5-1.8b-chat [----S] | Ctx: 32K @cf/qwen/qwen1.5-0.5b-chat [----S] | Ctx: 32K ## runwayml / text-to-image @cf/runwayml/stable-diffusion-v1-5-img2img [-----] @cf/runwayml/stable-diffusion-v1-5-inpainting [-----] ## stabilityai / text-to-image >>> @cf/stabilityai/stable-diffusion-xl-base-1.0 [-----] ## thebloke / text-generation @hf/thebloke/llama-2-13b-chat-awq [----S] | Ctx: 4K @cf/thebloke/discolm-german-7b-v1-awq [----S] | Ctx: 4K @hf/thebloke/mistral-7b-instruct-v0.1-awq [----S] | Ctx: 4K @hf/thebloke/neural-chat-7b-v3-1-awq [----S] | Ctx: 4K @hf/thebloke/openhermes-2.5-mistral-7b-awq [----S] | Ctx: 4K @hf/thebloke/zephyr-7b-beta-awq [----S] | Ctx: 4K @hf/thebloke/deepseek-coder-6.7b-base-awq [----S] | Ctx: 4K @hf/thebloke/deepseek-coder-6.7b-instruct-awq [----S] | Ctx: 4K ## tiiuae / text-generation @cf/tiiuae/falcon-7b-instruct [----S] | Ctx: 4K ## tinyllama / text-generation @cf/tinyllama/tinyllama-1.1b-chat-v1.0 [----S] | Ctx: 2K ## unum / image-to-text @cf/unum/uform-gen2-qwen-500m [-V---] ## zai-org / text-generation >>> @cf/zai-org/glm-4.7-flash [T---S] | Ctx: 131K