Azure is an API provider that hosts large language models. Active models: 4; From (input): $0.50 / 1M tok; Avg throughput: 95 tok/s; Avg latency: 0.59 s; Max context: 128K.

Azure currently serves 4 active models out of 11 historical offerings on LLM Stats.

Azure input pricing starts from $0.50 per 1M tokens, with the most expensive offering at $10 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

Azure averages 95 output tokens per second across its catalog, with average latency of 0.59s. Per-model performance is shown in the Performance tab.

Most providers expose an OpenAI-compatible /v1/chat/completions endpoint so you can switch from OpenAI to Azure by changing only the base URL and API key. Check https://azure.microsoft.com for the exact endpoint format and any provider-specific parameters.

Yes. Azure's catalog includes 2 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Azure hosts models from OpenAI and Microsoft. See the Models tab for the full catalog grouped by creator.

Sign up at https://azure.microsoft.com to get an API key, then call Azure's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at Azure's base URL with your key. Use the Pricing and Performance tabs above to pick the right model for your latency, cost, and context-window requirements.