Bedrock is an API provider that hosts large language models. Active models: 1; From (input): $15.00 / 1M tok; Avg throughput: 120 tok/s; Avg latency: 0.50 s; Max context: 200K.

Bedrock currently serves 1 active models out of 22 historical offerings on LLM Stats.

Bedrock input pricing starts from $15.00 per 1M tokens, with the most expensive offering at $15 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

Bedrock averages 120 output tokens per second across its catalog, with average latency of 0.50s. Per-model performance is shown in the Performance tab.

Yes. Bedrock's catalog includes 1 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

Bedrock hosts models from Anthropic, AI21 Labs, Amazon, Cohere, and Meta. See the Models tab for the full catalog grouped by creator.

Sign up at https://aws.amazon.com/bedrock/ to get an API key, then call Bedrock'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.