Skip to main content

Discover answers and insights from the Anthropic team

Search results for:tokens
How large is the Anthropic API’s context window?
The Anthropic API can ingest can ingest 1M tokens when using Sonnet 4, and 200K+ tokens (about 500 pages
About the Development Partner Program
tokens Cache read: -$0.09 per million tokens To be eligible for this discount, OAuth must… and 6% off of Claude Opus 4 and Claude Opus 4.1 Claude Code input tokens… Price reductions Standard input: -$0.9 per million tokens Cache write: -$1.125 per million
Our approach to API rate limits
tier, and is currently measured in three key metrics: Requests per minute (RPM) Input tokens… per minute (ITPM) Output tokens per minute (OTPM) If you exceed any of these rate limits,
How large is the context window on paid Claude plans?
Claude’s context window size is 200K, meaning it can ingest 200K+ tokens (about 500 pages of text or
What is the maximum prompt length?
for paid Claude plans, Claude for Work (Team and Enterprise) plans, and our API is currently 200k+ tokens
How do I use the Workbench?
This allows you to select the model, temperature, and max tokens to sample: After crafting your
How do I log out of all active sessions?
you used your Claude account to authenticate into Claude Code, you can manage your authorization tokens
Anthropic MCP Directory Policy
feedback rather than generic error messages. 15) MCP servers should be frugal with their use of tokens… The amount of tokens a given tool call uses should be roughly commensurate with the complexity or impact
Cost and Usage Reporting in Console
Usage Statistics: See total input and output tokens for your selected filters
About Claude's Pro Plan Usage
Every time you reference that content, cached tokens count less than uncached portions toward your usage