Expired50% confidenceFactExact time
Kimi K2.7 Code used 87.5k context tokens (33% of capacity) and consumed 2.6 million total tokens during the Cal.com bug fix task
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Kimi Code Advanced Tutorial: Video Understanding, Swarm Mode & ACP Protocol Practical Guide
bilibili技术爬爬虾6/23/2026
Related Claims
UnverifiedK2.6 wrote an inference engine from scratch on a Mac using the Zig language, taking 12 hours and over 4,000 tool calls, optimizing throughput from 15 tokens/s to 193 tokens/s, which is 20% faster than LM Studio.69% similarUnverifiedJust one week after Kimi K2.6 went live on OpenRouter, it surged to first place on the platform with 1.88T tokens in calls.64% similarUnverifiedThe entire Voxweaver Studio project development consumed 741K tokens, accounting for only 14% of Grok CLI's monthly available quota (in SuperGrok mode).63% similarUnverifiedKimi announced the full public release of K2.7 Code High Speed, with an output speed of approximately 180 tokens per second in typical programming scenarios—about 5 to 6 times that of the standard version—at 3 times the credit consumption of the standard version.62% similarUnverifiedLLM context windows have a fixed capacity limit such as 128K or 200K tokens61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41427API
curl https://kongchang.com/api/v1/knowledge/claims/41427MCP
get_claim(id=41427)