Skip to content
Sovyron

Cloudflare Workers AI

27 modelsProvider docs

As of Oct 4, 2026, Cloudflare Workers AI lists 27 supported models in the Sovyron catalog, including GLM-5.3-Flash, GLM-5.3, Qwen3.8 27B, DeepSeek V4 Pro 0813 and DeepSeek V4 Flash 0731 — glm-flash, glm, qwen, deepseek-thinking, deepseek-flash and kimi-k2 families. Its metered rates span $0.0408–$2.15 per 1M tokens on a 3:1 input:output blend, and every price in the table is Cloudflare Workers AI's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

27 of 27 models
Cloudflare Workers AI model prices in USD per 1M tokens, updated Oct 4, 2026
Model1M input1M output1M cache readContextReleased
GLM-5.3-Flash$0.15$0.5$0.031.0MAug 26, 2026
GLM-5.3$1.4$4.4$0.261.0MAug 14, 2026
Qwen3.8 27B$0.45$3.2$0.05262kAug 14, 2026
DeepSeek V4 Pro 0813$1.32$3.96$0.0441.0MAug 12, 2026
DeepSeek V4 Flash 0731$0.44$1.32$0.0141.0MJul 31, 2026
GLM-5.2$1.4$4.4$0.26262kJun 13, 2026
Kimi K2.7 Code$0.95$4$0.19262kJun 12, 2026
Kimi K2.6$0.95$4$0.16262kApr 21, 2026
Gemma 4 26B A4B IT$0.1$0.3$0.05256kApr 2, 2026
Nemotron 3 Super 120B$0.5$1.5—256kMar 11, 2026
GLM-4.7-Flash$0.0605$0.4—131kJan 19, 2026
Granite 4.0 H Micro$0.017$0.112—131kOct 2, 2025
Gemma Sea Lion V4 27B It$0.351$0.555—128kSep 23, 2025
GPT OSS 120B$0.35$0.75—128kAug 5, 2025
GPT OSS 20B$0.2$0.3—128kAug 5, 2025
Qwen3 30B A3b fp8$0.0509$0.335—33kApr 28, 2025
Llama 4 Scout 17B 16E Instruct$0.27$0.85—131kApr 5, 2025
Mistral Small 3.1 24B Instruct$0.351$0.555—128kMar 17, 2025
QwQ 32B$0.66$1—24kMar 5, 2025
DeepSeek R1 Distill Qwen 32B$0.497$4.881—80kJan 20, 2025
Llama 3.3 70B Instruct fp8 Fast$0.293$2.253—24kDec 6, 2024
Qwen2.5 Coder 32B Instruct$0.66$1—33kNov 12, 2024
Llama 3.2 11B Vision Instruct$0.0485$0.676—128kSep 25, 2024
Llama 3.2 1B Instruct$0.027$0.201—60kSep 25, 2024
Llama 3.2 3B Instruct$0.0509$0.335—80kSep 25, 2024
Llama 3.1 8B Instruct fp8$0.152$0.287—32kJul 23, 2024
Llama-Guard-3-8B$0.484$0.03—131kJul 23, 2024