Enhancement: New features on the Anthropic API reducing costs by up to 90%.

[tracer8]

What features would you like to see added?

New features on the Anthropic API reducing costs by up to 90%.

Several features are now generally available on the Anthropic API to help you better optimize for cost and speed, including:

Prompt caching

Provide Claude with more background knowledge and example outputs to improve response accuracy and latency—all while reducing costs by up to 90%.

Message Batches API

Send any number of batches of up to 100,000 messages per batch. Batches are processed asynchronously with results returned as soon as the batch is complete and cost 50% less than standard API calls.

Token counting

Determine the number of tokens in a message before sending it to Claude to make informed decisions about your prompts and usage.

Multimodal PDF support

Understand and analyze both text and visual content within PDF documents for more comprehensive analysis.

Models endpoint

List all available models to select between the latest Anthropic Models or query a specific model string to validate user-provided content.

More details

New features on the Anthropic API reducing costs by up to 90%.

Which components are impacted by your request?

No response

Pictures

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

Thanks. Prompt caching is already supported and some of these features already have open issues.

[tracer8]

Is caching automatic or i need to enable it by myself?

[danny-avila]

automatic and can be disabled

[tracer8]

thank you!