Cloudflare Workers AI model pricing
As of October 10, 2026, 29 Cloudflare Workers AI models are available through LiteLLM. The most recently added are Gemma 2B IT Lora, Gemma 4 26B A4B IT, Gemma 7B IT Lora. Prices below are Cloudflare Workers AI's list prices.
Cloudflare Workers AI models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| Gemma 2B IT Lora | Free | 8K | 1 | Jun 2026 | |
| Gemma 4 26B A4B IT | $0.10 / $0.30 per 1M tokens | 256K | 8 | Jun 2026 | |
| Gemma 7B IT Lora | Free | 4K | 1 | Jun 2026 | |
| GLM 5.2 | Z.ai | $1.40 / $4.40 per 1M tokens | 256K | 19 | Jun 2026 |
| Granite 4.0 H Micro | – | $0.017 / $0.112 per 1M tokens | 131K | 1 | Jun 2026 |
| Kimi K2.7 Code | Moonshot AI | $0.95 / $4 per 1M tokens | 256K | 14 | Jun 2026 |
| Llama 2 7B Chat HF Lora | Meta | Free | 8K | 1 | Jun 2026 |
| Llama 3.3 70B Instruct FP8 Fast | Meta | $0.293 / $2.253 per 1M tokens | 24K | 1 | Jun 2026 |
| Mistral 7B Instruct V0.2 Lora | Mistral AI | Free | 15K | 1 | Jun 2026 |
| Nemotron 3 120B A12B | NVIDIA | $0.50 / $1.50 per 1M tokens | 256K | 1 | Jun 2026 |
| Kimi K2.6 | Moonshot AI | $0.95 / $4 per 1M tokens | 256K | 13 | Apr 2026 |
| GLM 4.7 Flash | Z.ai | $0.0605 / $0.40 per 1M tokens | 128K | 5 | Feb 2026 |
| Gemma Sea Lion V4 27B IT | $0.351 / $0.555 per 1M tokens | 128K | 2 | Dec 2025 | |
| GPT OSS 120B | OpenAI | $0.35 / $0.75 per 1M tokens | 128K | 22 | Aug 2025 |
| GPT OSS 20B | OpenAI | $0.20 / $0.30 per 1M tokens | 128K | 14 | Aug 2025 |
| Qwen3 30B A3B | Alibaba | $0.0509 / $0.335 per 1M tokens | 32K | 9 | Jul 2025 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | $0.497 / $4.881 per 1M tokens | 80K | 5 | May 2025 |
| Llama Guard 3 8B | Meta | $0.484 / $0.03 per 1M tokens | 128K | 5 | May 2025 |
| QwQ 32B | Alibaba | $0.66 / $1 per 1M tokens | 24K | 7 | May 2025 |
| Llama 4 Scout 17B 16e Instruct | Meta | $0.27 / $0.85 per 1M tokens | 131K | 10 | Apr 2025 |
| Mistral Small 3.1 24B Instruct | Mistral AI | $0.351 / $0.555 per 1M tokens | 128K | 2 | Apr 2025 |
| Whisper Large V3 Turbo | OpenAI | $0 per second | – | 3 | Apr 2025 |
| Llama3.2 11B Vision Instruct | Meta | $0.0485 / $0.676 per 1M tokens | 128K | 5 | Nov 2024 |
| Qwen2.5 Coder 32B Instruct | Alibaba | $0.66 / $1 per 1M tokens | 32K | 6 | Nov 2024 |
| Llama 3.2 1B Instruct | Meta | $0.027 / $0.201 per 1M tokens | 60K | 5 | Oct 2024 |
| Llama3.2 3B Instruct | Meta | $0.0509 / $0.335 per 1M tokens | 80K | 8 | Oct 2024 |
| Llama 3.1 8B Instruct | Meta | $0.152 / $0.287 per 1M tokens | 32K | 13 | Jul 2024 |
| CodeLlama 7B Instruct | – | $1.923 / $1.923 per 1M tokens | 4K | 1 | Jan 2024 |
| Llama 2 7B Chat | Meta | $1.923 / $1.923 per 1M tokens | 3K | 2 | Jan 2024 |