At a glance

Bedrockpricing, performance & catalog

The citable facts about Bedrock's 2 models — sourced from provider APIs and refreshed continuously.

Lowest price
Nova 2 Lite at $0.300 per 1M input tokens
Largest context
Nova 2 Sonic at 1.0M tokens
Catalog
2 active models from 5 organizations

Fastest

No throughput data yet.

FAQ

Common questions about Bedrock.

What is Bedrock?

Bedrock is an API provider that hosts large language models. Active models: 2; From (input): $0.30 / 1M tok; Max context: 1.0M.

How many models does Bedrock offer?

Bedrock currently serves 2 active models out of 24 historical offerings on LLM Stats.

What is Bedrock's API pricing?

Bedrock input pricing starts from $0.30 per 1M tokens, with the most expensive offering at $0.33 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

Is Bedrock OpenAI compatible?

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

Does Bedrock support multimodal models?

Yes. Bedrock's catalog includes 1 vision-capable and 2 audio models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does Bedrock host?

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

How do I start using Bedrock?

Sign up at https://aws.amazon.com/bedrock/ to get an API key, then call Bedrock's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at Bedrock'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.