Models by capability

These are the Amazon Bedrock models that can call functions — the prerequisite for anything agentic. A model without tool use can answer from what is in the prompt, but it cannot look something up, take an action, or drive a loop.

28% of the catalogue · from $0.035 per 1M input

These Amazon Bedrock models accept images as input: screenshots, scanned documents, charts, photographs and UI captures. Everything else on Bedrock is text-in, and needs an OCR step before it can read a scanned PDF.

35% of the catalogue · from $0.040 per 1M input

These Amazon Bedrock models support prompt caching: a prefix you send repeatedly is stored server-side and re-read at a fraction of the input price. For anything that resends a long system prompt — agents, RAG with a fixed instruction block, chat with history — this is the single largest lever on the bill.

18% of the catalogue · from $0.035 per 1M input

These Amazon Bedrock models support batch inference, which processes a submitted job asynchronously at roughly half the on-demand token rate. If the work can wait hours rather than seconds, this is the simplest halving of a token bill available on the platform.

48% of the catalogue · from $0.035 per 1M input

These Amazon Bedrock models accept at least 200,000 tokens in a single call — roughly a 500-page book, a large codebase, or a full day of meeting transcripts. Above that threshold you can usually stop chunking and let the model see the whole thing.

22% of the catalogue · from $0.060 per 1M input

These Amazon Bedrock models turn text into vectors for semantic search, clustering and deduplication. They do not generate text — an embedding model is the retrieval half of a RAG system, and always needs a text model beside it to answer with.

9% of the catalogue · from $0.100 per 1M input

These Amazon Bedrock models can be customised on your own data — fine-tuning or continued pre-training — producing a private model only your account can invoke.

1% of the catalogue