Models32
- Cheapest for
- 2 models
- Serves
- 2 model types
Monthly visits—
Models by type
Models on Cloudflare Workers AI
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
 GLM-5.3Zhipu AI | $1.40/1M | $4.40/1M from $1.10 at NanoGPT | ±0% | — |
| GLM-5.3-FlashZhipu AI | $0.15/1M | $0.50/1M from $0.20 at APIMart | ±0% | — |
 Qwen3.8 27BAlibaba | $0.45/1M | $3.20/1M from $0.50 at EmpirioLabs AI | +7% | — |
| GLM-5.2Zhipu AI | $1.40/1M | $4.40/1M from $1.80 at Deep Infra | ±0% | — |
 DeepSeek V4 Flash Vision ExpDeepSeek | $0.30/1M | $1.20/1M from $0.294 at Deep Infra | +100% | — |
| GPT OSS 120BOpenAI | $0.35/1M | $0.75/1M from $0.14 at Requesty | +436% | — |
| DeepSeek R1DeepSeek | $0.497/1M | $4.88/1M from $1.79 at APIMart | +172% | — |
| Kimi K2.5Moonshot AI | $0.60/1M | $3/1M from $0.555 at APIMart | +440% | — |
| GPT OSS 20BOpenAI | $0.20/1M | $0.30/1M from $0.09 at OpenRouter | +233% | — |
| Kimi K2.6Moonshot AI | $0.95/1M | $4/1M from $2.40 at APIYI | +7% | — |
 Llama 4 Scout 17B InstructMeta | $0.27/1M | $0.85/1M from $0.20 at AIHubMix | +325% | — |
| GLM-4.7-FlashZhipu AI | $0.06/1M | $0.40/1M | ±0% | — |
| Kimi K2.7 Code HighSpeedMoonshot AI | $0.95/1M | $4/1M from $2.76 at Kenari | +7% | — |
| Qwen3 30B A3BAlibaba | $0.051/1M | $0.335/1M from $0.29 at Helicone | +16% | — |
| Llama-3.3-70B-InstructMeta | $0.293/1M | $2.25/1M from $0.32 at Deep Infra | +604% | — |
| DeepSeek V4 Flash 0731DeepSeek | $0.44/1M | $1.32/1M from $0.133 at OpenRouter | +890% | — |
| Llama 3.1 8B InstructMeta | $0.282/1M | From$0.827/1M from $0.05 at Helicone | +1554% | — |
 Gemma 4 26B A4B ITGoogle | $0.10/1M | $0.30/1M from $0.225 at OpenRouter | -50% | — |
| Gemma 3 12B ITGoogle | $0.345/1M | $0.556/1M from $0.10 at Helicone | +456% | — |
 Nemotron 3 Super 120B A12BNVIDIA | $0.50/1M | $1.50/1M from $0.40 at Deep Infra | — | — |
| DeepSeek V4 ProDeepSeek | $1.32/1M | $3.96/1M from $1.58 at CometAPI | +100% | — |
 Gemma SEA-LION v4 27BAI Singapore | $0.351/1M | $0.555/1M from $0.40 at Hugging Face | +39% | — |
| Granite 4.0 H MicroIBMCheapest | $0.017/1M | $0.112/1M | — | — |
| Llama 3.2 11B Vision InstructMeta | $0.049/1M | $0.676/1M from $0.20 at AIHubMix | +238% | — |
| Llama 3.2 1B InstructMeta | $0.027/1M | $0.201/1M from $0.10 at Amazon Bedrock | +101% | — |
| Llama 3.2 3B InstructMeta | $0.051/1M | $0.335/1M from $0.05 at DevPass (LLM Gateway) | +570% | — |
| Llama Guard 3 8BMetaCheapest | $0.484/1M | $0.03/1M | — | — |
| Llama3 8B InstructMeta | $0.123/1M | From$0.266/1M from $0.25 at Replicate | +6% | — |
 Mistral Small 3.1 24BMistral | $0.351/1M | $0.555/1M from $0.33 at Requesty | +68% | — |
| Mistral-7B-Instruct-v0.1MistralCheapest | $0.11/1M | $0.19/1M | — | — |
| Qwen2.5-Coder-32B-InstructAlibaba | $0.66/1M | $1/1M from $0.16 at AIHubMix | +525% | — |
| Qwq 32BAlibaba | $0.66/1M | $1/1M from $0.56 at AIHubMix | +79% | — |
Cloudflare Workers AI at a glance
32 models in total: 31 text, 1 moderation. The cheapest is Llama Guard 3 8B at $0.03 /1M. Llama 4 Scout 17B Instruct has the largest context window, 1.31M tokens. The most searched is GLM-5.3, with about 276K Google searches a month. The newest is DeepSeek V4 Flash Vision Exp, released Oct 17, 2026.
Cheapest
- Llama Guard 3 8B$0.03/1M
- Granite 4.0 H Micro$0.112/1M
- Mistral-7B-Instruct-v0.1$0.19/1M
- Llama 3.2 1B Instruct$0.201/1M
- Llama3 8B Instruct$0.266/1M
Largest context
- Llama 4 Scout 17B Instruct1.31M
- GLM-5.31.05M
- GLM-5.3-Flash1.05M
- DeepSeek V4 Flash Vision Exp1.05M
- DeepSeek V4 Flash 07311.05M
Most searched
- GLM-5.3276K
- GLM-5.3-Flash121K
- Qwen3.8 27B120K
- GLM-5.2109K
- DeepSeek V4 Flash Vision Exp47K
Newest
- DeepSeek V4 Flash Vision ExpOct 17, 2026
- GLM-5.3Aug 25, 2026
- GLM-5.3-FlashAug 25, 2026
- Qwen3.8 27BAug 5, 2026
- DeepSeek V4 Flash 0731Jul 31, 2026