Unverified50% confidenceCautionExact time
The minimum cacheable length for Haiku 5.5 is 512 tokens, and prompts shorter than this will not error but will not be cached; a cache entry only becomes available after the first response begins; by default the cache lives for 5 minutes and is refreshed for free on each hit.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedWhen the context approaches 512K tokens, the prefill-decode disaggregated architecture ensures that users still receive the first response token within 800 milliseconds after reading an entire specification.65% similarUnverifiedThe embedding model's maximum length means that inputs exceeding 512 tokens are silently truncated, so the example sets the chunk budget to 480 tokens.64% similarUnverifiedClaude Haiku 5.5's context window has expanded from Haiku 4.5's 200,000 tokens to 1 million tokens, and the output limit has been raised from 64K to 128K.62% similarUnverifiedLocal model inference is slow (approximately 1–5 tokens/second) while the cloud can reach 50+ tokens/second; local models have a lower capability ceiling but incur no API costs or privacy concerns.62% similarUnverifiedIn an AWS sample application, across 28 calls reviewing the same document, CloudWatch recorded 196,680 tokens written to cache and 0 reads, because the cache point was placed after each entry's own instructions; after moving the cache point to after the document, the second entry immediately became a read of 4,624 tokens.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034448API
curl https://kongchang.com/api/v1/knowledge/claims/1034448MCP
get_claim(id=1034448)