Cloudflare Workers AI

Inference layers 47 models data_array 262K max context Free credits

info Notes

10,000 Neurons/day free, no credit card required. 75+ models available on the free tier. []

key How to get API key

General steps — follow the official Cloudflare Workers AI page for exact details.

  1. Open the Cloudflare Workers AI API key page ↗
  2. Create a new account, or sign in if you already have one.
  3. Generate an API key from the dashboard or settings.

layers Available models 47

search
ModelCapabilitiesContextOutputRate limit
`@cf/meta/llama-3.3-70b-instruct-fp8-fast` `@cf/meta/llama-3.3-70b-instruct-fp8-fast`
description
24K—10K neurons/day (shared)
`@cf/meta/llama-4-scout-17b-16e-instruct` `@cf/meta/llama-4-scout-17b-16e-instruct`
Multimodal
131K—10K neurons/day (shared)
`@cf/openai/gpt-oss-120b` `@cf/openai/gpt-oss-120b`
description
128K—10K neurons/day (shared)
`@cf/google/gemma-4-26b-a4b-it` `@cf/google/gemma-4-26b-a4b-it`
description visibility
256K—10K neurons/day (shared)
`@cf/zai-org/glm-4.7-flash` `@cf/zai-org/glm-4.7-flash`
description
131K—10K neurons/day (shared)
`@cf/mistralai/mistral-small-3.1-24b-instruct` `@cf/mistralai/mistral-small-3.1-24b-instruct`
description
128K—10K neurons/day (shared)
`@cf/deepseek-ai/deepseek-r1-distill-qwen-32b` `@cf/deepseek-ai/deepseek-r1-distill-qwen-32b`
Text (reasoning)
80K—10K neurons/day (shared)
+ 72 more models +-72-more-models
Text, Image, Audio, Embeddings
Varies—10K neurons/day (shared)
GPT-OSS 120B gpt-oss-120b
description
262K—10,000 neurons per day
Qwen 3.8 27B qwen-3.8-27b
description
262K—10,000 neurons per day
GPT-OSS 20B gpt-oss-20b
description
262K—10,000 neurons per day
Llama 3.3 70B llama-3.3-70b
description
262K—10,000 neurons per day
Llama 4 Scout llama-4-scout
description
262K—10,000 neurons per day
Llama 3.1 8B Fast llama-3.1-8b-fast
description
262K—10,000 neurons per day
Llama 3.1 8B FP8 llama-3.1-8b-fp8
description
262K—10,000 neurons per day
Llama 3.2 11B Vision llama-3.2-11b-vision
description
262K—10,000 neurons per day
Llama 3.2 1B llama-3.2-1b
description
262K—10,000 neurons per day
Llama 3.2 3B llama-3.2-3b
description
262K—10,000 neurons per day
Gemma 4 26B gemma-4-26b
description
262K—10,000 neurons per day
GLM 4.7 Flash glm-4.7-flash
description
262K—10,000 neurons per day
Granite 4.0 H Micro granite-4.0-h-micro
description
262K—10,000 neurons per day
Nemotron 3 Super nemotron-3-super
description
262K—10,000 neurons per day
Qwen 3 30B A3B qwen-3-30b-a3b
description
262K—10,000 neurons per day
Qwen 2.5 Coder 32B qwen-2.5-coder-32b
description
262K—10,000 neurons per day
QwQ 32B qwq-32b
description
262K—10,000 neurons per day
Mistral Small 3.1 mistral-small-3.1
description
262K—10,000 neurons per day
DeepSeek R1 Distill 32B deepseek-r1-distill-32b
description
262K—10,000 neurons per day
Llama Guard 3 8B llama-guard-3-8b
description
262K—10,000 neurons per day
Whisper Large V3 Turbo whisper-large-v3-turbo
description
262K—10,000 neurons per day
BGE M3 bge-m3
description
262K—10,000 neurons per day
BGE Base bge-base
description
262K—10,000 neurons per day
EmbeddingGemma 300M embeddinggemma-300m
description
262K—10,000 neurons per day
FLUX.1 Schnell flux.1-schnell
description
262K—10,000 neurons per day
Qwen 3 Embedding 0.6B qwen-3-embedding-0.6b
description
262K—10,000 neurons per day
Gemma 3 12B gemma-3-12b
description
262K—10,000 neurons per day
Llama 3.1 8B llama-3.1-8b
description
262K—10,000 neurons per day
Mistral 7B mistral-7b
description
262K—10,000 neurons per day
LLaVA 1.5 7B llava-1.5-7b
description
262K—10,000 neurons per day
Whisper whisper
description
262K—10,000 neurons per day
Nova 3 nova-3
description
262K—10,000 neurons per day
MeloTTS melotts
description
262K—10,000 neurons per day
Stable Diffusion XL stable-diffusion-xl
description
262K—10,000 neurons per day
Resnet 50 resnet-50
description
262K—10,000 neurons per day
BART Large CNN bart-large-cnn
description
262K—10,000 neurons per day
DistilBERT SST 2 distilbert-sst-2
description
262K—10,000 neurons per day
SQLCoder 7B sqlcoder-7b
description
262K—10,000 neurons per day
Phi 2 phi-2
description
262K—10,000 neurons per day

help Frequently Asked Questions

Cloudflare Workers AI offers 47 free models.

The largest context window is 262,000 tokens.

The free tier is limited to 10,000 neurons per day.

No, Cloudflare Workers AI does not require a credit card for the free tier.