Unverified50% confidenceBenchmarkExact time
The hosted-side usage across the 400 cases totals 1,222,211 tokens (290,606 input, 931,605 output), i.e. 3,055.5 tokens per case.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedMost models have a single output limit of between 4,000 and 8,000 tokens, with some high-end models supporting up to 32,000 tokens.71% similarUnverifiedA log study measured the tokens each harness sends before reading the user's prompt: OpenCode approximately 7,000 tokens, CloudCode approximately 33,000 tokens, and Pi approximately 1,300 tokens.70% similarUnverifiedIn a text generation test using an 8-billion-parameter model, the M5 Ultra achieved 188 tokens per second versus 129 tokens per second for the M3 Ultra, representing only 1.45x.67% similarUnverifiedMistral Large 4 has a context window of 500,000 tokens and a speed of approximately 116 tokens/second.67% similarUnverifiedUnder this configuration, the 35B model achieves a measured single-user peak speed of approximately 80 tokens/second, with concurrent throughput exceeding 500 tokens/second.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017000API
curl https://kongchang.com/api/v1/knowledge/claims/1017000MCP
get_claim(id=1017000)