LLM Opex

LLM hosting inside Italy

Which clouds run language models inside Italy, which models each sells there per token, and at what price. A price here is for a region in the country: data sent to the model does not leave it.

Clouds with a region in the country

No region in the country: Alibaba Cloud, Anthropic, Cloudflare, Core42, Crusoe, Databricks, DeepInfra, Fireworks AI, Gemini API, Groq, HF Endpoints, Huawei Cloud, IBM watsonx, Mistral, Nebius, OpenAI, Snowflake, Telnyx, Together AI, xAI.

Models sold in the country, per token

US dollars per million tokens, input and output.
ModelAWSAzureGoogle CloudOCI
Amazon Nova Lite$0.096 in / $0.384 out———
Amazon Nova Pro$1.28 in / $5.21 out———
Claude Fable 5$10.00 in / $50.00 out———
Claude Fable 5.1$10.00 in / $50.00 out———
Claude Haiku 4.5$1.00 in / $5.00 out———
Claude Opus 4.5$5.00 in / $25.00 out———
Claude Opus 4.6$5.00 in / $25.00 out———
Claude Opus 4.7$5.00 in / $25.00 out———
Claude Opus 4.8$5.00 in / $25.00 out———
Claude Opus 5$5.00 in / $25.00 out———
Claude Opus 5.5$4.00 in / $20.00 out———
Claude Sonnet 4.5$3.00 in / $15.00 out———
Claude Sonnet 4.6$3.00 in / $15.00 out———
Claude Sonnet 5$2.00 in / $10.00 out———
Claude Sonnet 5.5$2.00 in / $10.00 out———
Cohere Command A—$0.80 in / $3.20 out——
DeepSeek V3.1$0.696 in / $2.02 out———
DeepSeek V3.2$0.74 in / $2.22 out$0.62 in / $1.85 out——
DeepSeek V4 Flash—$0.15 in / $0.31 out——
DeepSeek V4 Pro—$1.93 in / $3.83 out——
DeepSeek V4.1 Flash—$0.375 in / $1.50 out——
GLM 5$1.20 in / $3.84 out$1.10 in / $3.52 out——
GLM 5.1—$1.54 in / $4.84 out——
GLM 5.2—$1.54 in / $4.84 out——
GLM 5.3—$1.75 in / $5.50 out——
GLM 5.3 Flash—$0.188 in / $0.625 out——
GPT-4.1—$2.00 in / $8.00 out——
GPT-4.1 mini—$0.40 in / $1.60 out——
GPT-5 mini—$0.25 in / $2.00 out——
GPT-5 nano—$0.05 in / $0.40 out——
GPT-6 Astra—$10.00 in / $50.00 out——
Kimi K2.5$0.72 in / $3.60 out$0.66 in / $3.30 out——
Kimi K2.6—$1.04 in / $4.40 out——
Kimi K2.7 Code—$1.05 in / $4.40 out——
Kimi K3$3.00 in / $15.00 out$3.00 in / $15.00 out——
Llama 3.1 405B———$10.68 in / $10.68 out
Llama 3.3 70B—$0.71 in / $0.71 out——
Llama 4 Maverick 17B—$0.25 in / $1.00 out——
MiniMax M2.5$0.36 in / $1.44 out$0.33 in / $1.32 out——
Mistral Large$0.60 in / $1.80 out———
OpenAI gpt-oss 120B$0.20 in / $0.79 out$0.15 in / $0.60 out——
OpenAI gpt-oss 20B$0.09 in / $0.40 out$0.07 in / $0.30 out——
Qwen3 235B A22B$0.29 in / $1.16 out———
Qwen3 32B$0.20 in / $0.79 out$0.30 in / $1.20 out——

List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.