Google is an API provider that hosts large language models. Active models: 17; From (input): $0.25 / 1M tok; Avg throughput: 78 tok/s; Avg latency: 0.60 s; Max context: 1.0M.

Google currently serves 17 active models out of 40 historical offerings on LLM Stats.

Google input pricing starts from $0.25 per 1M tokens, with the most expensive offering at $15 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

Google averages 78 output tokens per second across its catalog, with average latency of 0.60s. Per-model performance is shown in the Performance tab.

Yes. Google's catalog includes 20 vision-capable, 13 image generation, and 10 video models. See the Models and Capabilities tabs for the full per-model breakdown.

Google hosts models from Anthropic, Google, AI21 Labs, Meta, and Mistral AI. See the Models tab for the full catalog grouped by creator.

Sign up at https://ai.google.dev to get an API key, then call Google's API directly from your application. Use the Pricing and Performance tabs above to pick the right model for your latency, cost, and context-window requirements.