Unverified50% confidenceBenchmarkExact time
When serving Kimi K2.5 at 100 tokens/second, Jalapeño's throughput is close to 9 times that of the second-place competitor, with a peak throughput of up to 700 tokens/second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedThe description text for 60 Skills/MCPs totals approximately 12,000 tokens (an average of 200 tokens each).60% similarUnverifiedIn a typical scenario of 20 rounds of interaction, if the system prompt occupies 15,000 tokens and each round produces an average of 2,000 tokens, by the 20th round the input token count for a single request balloons to 55,000 tokens.58% similarUnverifiedThe batch-scoring step processes approximately 10 abstracts per batch, totaling about 18,000 tokens.55% similarUnverified在一个典型项目查询中发送了45,000 tokens的上下文，但真正有用的只有约5,000 tokens54% similarUnverified100万Token意味着模型理论上可一次性处理约50-75万汉字54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/945796API
curl https://kongchang.com/api/v1/knowledge/claims/945796MCP
get_claim(id=945796)