Claude Sonnet 4 has been upgraded, and it may now keep in mind as much as 1 million tokens of context, however solely when it is used through API. This might change sooner or later.
That is 5x greater than the earlier restrict. It additionally signifies that Claude now helps remembering over 75,000 strains of code, and even a whole bunch of paperwork in a single session.
Beforehand, you had been required to submit particulars to Claude in small chunks, however that additionally meant Claude would overlook the context because it hit the restrict. With as much as a 1 million context restrict, you’ll be able to construct higher apps, and Claude can keep in mind extra of your code than ever.
It’s value noting that the 1 million context restrict is restricted to Sonnet 4. Opus 4.1 nonetheless has the previous limitations as a result of it is an costly mannequin.
Solely API will get 1 million tokens context restrict
The brand new context restrict is rolling out through the Anthropic API for purchasers with Tier 4 and customized charge limits, with broader availability rolling out over the approaching weeks.
“Lengthy context can also be obtainable in Amazon Bedrock and is coming quickly to Google Cloud’s Vertex AI,” Anthropic famous.
“With 1M tokens you’ll be able to: load whole codebases with all dependencies, analyze a whole bunch of paperwork without delay, and construct brokers that preserve context throughout a whole bunch of instrument calls. Pricing adjusts for prompts over 200K tokens, however immediate caching can scale back prices and latency.”
Claude’s cellular and internet apps might be getting the 1 million token context restrict in some unspecified time in the future sooner or later.
46% of environments had passwords cracked, almost doubling from 25% final 12 months.
Get the Picus Blue Report 2025 now for a complete have a look at extra findings on prevention, detection, and information exfiltration tendencies.
