Cloudflare Workers AI
17 modelsProvider docs
As of Nov 22, 2026, Cloudflare Workers AI lists 17 supported models in the Sovyron catalog, including Inkling 2 Small, Clairic Flash, DeepSeek V4.1 Flash 1017, GLM-5.3 and Qwen3.8 27B across the inkling-small, deepseek-flash, glm, qwen, gemma and glm-flash families. The cheapest rate in the table is Llama-Guard-3-8B at $0.03 per 1M output tokens, the priciest GLM-5.3 at $4.4. On a 3:1 input:output blend the metered rates span $0.0408–$2.15 per 1M tokens, and every price is Cloudflare Workers AI's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
17 of 17 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Inkling 2 Small | $0.3 | $1 | $0.1 | 1.0M | Nov 9, 2026 |
| Clairic Flash | $0.1 | free | — | 66k | Oct 29, 2026 |
| DeepSeek V4.1 Flash 1017 | $0.3 | $1.2 | $0.006 | 1.0M | Oct 17, 2026 |
| GLM-5.3 | $1.4 | $4.4 | $0.26 | 1.0M | Aug 14, 2026 |
| Qwen3.8 27B | $0.45 | $3.2 | $0.05 | 262k | Aug 14, 2026 |
| Gemma 4 26B A4B IT | $0.1 | $0.3 | $0.05 | 256k | Apr 2, 2026 |
| GLM-4.7-Flash | $0.0605 | $0.4 | — | 131k | Jan 19, 2026 |
| Granite 4.0 H Micro | $0.017 | $0.112 | — | 131k | Oct 2, 2025 |
| Gemma Sea Lion V4 27B It | $0.351 | $0.555 | — | 128k | Sep 23, 2025 |
| GPT OSS 120B | $0.35 | $0.75 | — | 128k | Aug 5, 2025 |
| GPT OSS 20B | $0.2 | $0.3 | — | 128k | Aug 5, 2025 |
| Llama 4 Scout 17B 16E Instruct | $0.27 | $0.85 | — | 131k | Apr 5, 2025 |
| Mistral Small 3.1 24B Instruct | $0.351 | $0.555 | — | 128k | Mar 17, 2025 |
| Llama 3.3 70B Instruct fp8 Fast | $0.293 | $2.253 | — | 24k | Dec 6, 2024 |
| Qwen2.5-Coder-32B-Instruct | $0.66 | $1 | — | 33k | Nov 12, 2024 |
| Llama 3.2 11B Vision Instruct | $0.0485 | $0.676 | — | 128k | Sep 25, 2024 |
| Llama-Guard-3-8B | $0.484 | $0.03 | — | 131k | Jul 23, 2024 |