Cloudflare Workers AI models and pricing
We track 16 models on Cloudflare Workers AI from 10 labs. The cheapest paid model is Granite 4.0 H Micro, at $0.02 per million input tokens and $0.11 per million output tokens. Input prices range from $0.02 to $1.40 and output prices from $0.03 to $4.40 per million tokens. The largest context window is 1M tokens (Inkling 2 Small, DeepSeek V4.1 Flash 1017 and GLM-5.3). Prices last verified 18 Nov 2026.
Prices in USD per million tokens. Official site
Cheapest models on Cloudflare Workers AI
- Granite 4.0 H Micro$0.02 / $0.11
- Gemma 4 26B A4B IT$0.10 / $0.30
- GLM-4.7-Flash$0.06 / $0.40
- gpt-oss-20b$0.20 / $0.30
- Llama Guard 3 8B$0.48 / $0.03
Input / output per million tokens, paid models, by combined price.
Newest models on Cloudflare Workers AI
- Inkling 2 Small5 Nov 2026
- DeepSeek V4.1 Flash 101717 Oct 2026
- Qwen3.8 27B14 Aug 2026
- GLM-5.314 Aug 2026
- Gemma 4 26B A4B IT2 Apr 2026
By the lab's release date.
All Cloudflare Workers AI models and prices
| Model | Lab | Input | Output | Context | Source |
|---|---|---|---|---|---|
| Inkling 2 Small @cf/thinkingmachines/inkling-2-small | Thinkingmachines | $0.30 | $1 | 1M | models.dev |
| DeepSeek V4.1 Flash 1017 @cf/deepseek-ai/deepseek-v4.1-flash-1017 | DeepSeek | $0.30 | $1.20 | 1M | models.dev |
| Qwen3.8 27B @cf/qwen/qwen3.8-27b | Alibaba (Qwen) | $0.45 | $3.20 | 262K | models.dev |
| GLM-5.3 @cf/zai-org/glm-5.3 | Zhipu AI (Z.ai) | $1.40 | $4.40 | 1M | models.dev |
| Gemma 4 26B A4B IT @cf/google/gemma-4-26b-a4b-it | Google DeepMind | $0.10 | $0.30 | 256K | models.dev |
| GLM-4.7-Flash @cf/zai-org/glm-4.7-flash | Zhipu AI (Z.ai) | $0.06 | $0.40 | 131K | models.dev |
| Granite 4.0 H Micro @cf/ibm-granite/granite-4.0-h-micro | IBM | $0.02 | $0.11 | 131K | models.dev |
| Gemma Sea Lion V4 27B It @cf/aisingapore/gemma-sea-lion-v4-27b-it | Aisingapore | $0.35 | $0.56 | 128K | models.dev |
| gpt-oss-20b @cf/openai/gpt-oss-20b | OpenAI | $0.20 | $0.30 | 128K | models.dev |
| gpt-oss-120b @cf/openai/gpt-oss-120b | OpenAI | $0.35 | $0.75 | 128K | models.dev |
| Llama-4-Scout-17B-16E-Instruct-FP8 @cf/meta/llama-4-scout-17b-16e-instruct | Meta | $0.27 | $0.85 | 131K | models.dev |
| Mistral Small 3.1 24B @cf/mistralai/mistral-small-3.1-24b-instruct | Mistral AI | $0.35 | $0.56 | 128K | models.dev |
| Llama-3.3-70B-Instruct @cf/meta/llama-3.3-70b-instruct-fp8-fast | Meta | $0.29 | $2.25 | 24K | models.dev |
| Qwen2.5-Coder-32B-Instruct @cf/qwen/qwen2.5-coder-32b-instruct | Alibaba (Qwen) | $0.66 | $1 | 33K | models.dev |
| Llama 3.2 11b Vision Instruct @cf/meta/llama-3.2-11b-vision-instruct | Meta | $0.05 | $0.68 | 128K | models.dev |
| Llama Guard 3 8B @cf/meta/llama-guard-3-8b | Meta | $0.48 | $0.03 | 131K | models.dev |
Frequently asked questions
How much does Cloudflare Workers AI cost per million tokens?
Prices on Cloudflare Workers AI depend on the model. Across the 16 models we track, input costs $0.02 to $1.40 per million tokens and output costs $0.03 to $4.40 per million tokens. Prices last verified 18 Nov 2026.
What is the cheapest model on Cloudflare Workers AI?
Granite 4.0 H Micro from IBM is the cheapest paid model we track on Cloudflare Workers AI, at $0.02 per million input tokens and $0.11 per million output tokens. Next are Gemma 4 26B A4B IT ($0.10 / $0.30) and GLM-4.7-Flash ($0.06 / $0.40). Prices last verified 18 Nov 2026.
How many models does Cloudflare Workers AI offer?
We currently track 16 active models on Cloudflare Workers AI from 10 labs, led by Meta (4), Alibaba (Qwen) (2), OpenAI (2) and Zhipu AI (Z.ai) (2).
Which model on Cloudflare Workers AI has the largest context window?
Inkling 2 Small, DeepSeek V4.1 Flash 1017 and GLM-5.3 share the largest context window we track on Cloudflare Workers AI: 1,048,576 tokens (1M).