Cloudflare Workers AI
- Categories
- Inference hosts
- Owned by
- Cloudflare, Inc. (NYSE: NET) · also owns Cloudflare AI Gateway
- HQ
- US
- Website
- https://developers.cloudflare.com/workers-ai/
- Pricing page
- https://developers.cloudflare.com/workers-ai/platform/pricing/
- Fee model
- per_token
- Fees
- Billed in Neurons at $0.011 per 1,000 Neurons; docs publish an equivalent USD per-M-token price per model (recorded in offers). Frontier models (Kimi K2.6/K2.7-code, GLM-5.2/5.3/5.3-flash, DeepSeek V4 Flash/Pro) require Workers Paid or prepaid AI Gateway credits
- Free tier
- 10,000 Neurons/day free on Workers Free and Workers Paid
- OpenAI-compatible API
- yes
- Notes
- Serverless on Cloudflare edge GPUs; daily limits reset 00:00 UTC; paying with AI Gateway credits gives higher rate limits on frontier models. OpenAI-compatible endpoint available. Context per model not captured from pricing page
- Sources
- https://developers.cloudflare.com/workers-ai/platform/pricing/ collected 2026-09-18
LLM prices (28 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 @cf/deepseek-ai/deepseek-v4-flash-0731 |
$0.44 | $1.32 | $0.014 | — | ✓ src |
| DeepSeek V4 Pro 0813 @cf/deepseek-ai/deepseek-v4-pro-0813 |
$1.32 | $3.96 | $0.044 | — | ✓ src |
| deepseek-r1-distill-qwen-32b @cf/deepseek-ai/deepseek-r1-distill-qwen-32b |
$0.497 | $4.88 | — | — | ✓ src |
| Gemma 3 12B IT @cf/google/gemma-3-12b-it |
$0.345 | $0.556 | — | — | ✓ src |
| Gemma 4 26B A4B @cf/google/gemma-4-26b-a4b-it |
$0.10 | $0.30 | — | — | ✓ src |
| GLM 4.7 Flash @cf/zai-org/glm-4.7-flash |
$0.06 | $0.40 | — | — | ✓ src |
| GLM-5.2 @cf/zai-org/glm-5.2 |
$1.40 | $4.40 | $0.26 | — | ✓ src |
| GLM-5.3 @cf/zai-org/glm-5.3 |
$1.40 | $4.40 | $0.26 | — | ✓ src |
| GLM-5.3 Flash @cf/zai-org/glm-5.3-flash |
$0.15 | $0.50 | $0.03 | — | ✓ src |
| gpt-oss-120b @cf/openai/gpt-oss-120b |
$0.35 | $0.75 | — | — | ✓ src |
| gpt-oss-20b @cf/openai/gpt-oss-20b |
$0.20 | $0.30 | — | — | ✓ src |
| granite-4.0-h-micro @cf/ibm-granite/granite-4.0-h-micro |
$0.017 | $0.112 | — | — | ✓ src |
| Kimi K2.5 @cf/moonshotai/kimi-k2.5 |
$0.60 | $3 | $0.10 | — | ✓ src |
| Kimi K2.6 @cf/moonshotai/kimi-k2.6 |
$0.95 | $4 | $0.16 | — | ✓ src |
| Kimi K2.7 Code @cf/moonshotai/kimi-k2.7-code |
$0.95 | $4 | $0.19 | — | ✓ src |
| Llama 3.1 70B Instruct @cf/meta/llama-3.1-70b-instruct-fp8-fast |
$0.293 | $2.25 | — | — | ✓ src |
| Llama 3.1 8B Instruct @cf/meta/llama-3.1-8b-instruct-fp8-fast |
$0.045 | $0.384 | — | — | ✓ src |
| Llama 3.2 1B Instruct @cf/meta/llama-3.2-1b-instruct |
$0.027 | $0.201 | — | — | ✓ src |
| Llama 3.2 3B Instruct @cf/meta/llama-3.2-3b-instruct |
$0.051 | $0.335 | — | — | ✓ src |
| Llama 3.3 70B Instruct @cf/meta/llama-3.3-70b-instruct-fp8-fast |
$0.293 | $2.25 | — | — | ✓ src |
| Llama 4 Scout 17B Instruct @cf/meta/llama-4-scout-17b-16e-instruct |
$0.27 | $0.85 | — | — | ✓ src |
| mistral-7b-instruct-v0.1 @cf/mistral/mistral-7b-instruct-v0.1 |
$0.11 | $0.19 | — | — | ✓ src |
| mistral-small-3.1-24b-instruct @cf/mistralai/mistral-small-3.1-24b-instruct |
$0.351 | $0.555 | — | — | ✓ src |
| Nemotron 3 Super 120B A12B @cf/nvidia/nemotron-3-120b-a12b |
$0.50 | $1.50 | — | — | ✓ src |
| qwen2.5-coder-32b-instruct @cf/qwen/qwen2.5-coder-32b-instruct |
$0.66 | $1 | — | — | ✓ src |
| Qwen3 30B A3B @cf/qwen/qwen3-30b-a3b-fp8 |
$0.051 | $0.335 | — | — | ✓ src |
| Qwen3.8-27B @cf/qwen/qwen3.8-27b |
$0.45 | $3.20 | — | — | ✓ src |
| qwq-32b @cf/qwen/qwq-32b |
$0.66 | $1 | — | — | ✓ src |