Unverified50% confidenceFactExact time
469 tok/s means that generating 500 tokens takes just over 1 second.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn this test, the prefill speed was fixed at approximately 500–600 tokens/s, and the time to first token increased linearly with input length.75% similarUnverifiedAfter switching to Max, the average token count surged to 5,000 (more than 10×), average latency rose to 50 seconds, and the slowest response reached 600 seconds.71% similarUnverified对于500 Token的回答，流式输出可以让用户在首Token延迟（约500ms）后就开始看到内容，而非等待完整生成（约10秒）69% similarUnverifiedIt is generally considered that single-concurrency output above 100 tokens/second is sufficient to achieve a smooth typewriter effect, and at approximately 200 tokens/second, generating a 2,000-character long text takes only about 10 seconds.67% similarUnverifiedOn an 8GB GPU, the token generation speed is approximately 4.2 to 5 tokens/second, and decreases from around 6 tokens/second to approximately 4.2 as the context grows longer.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972285API
curl https://kongchang.com/api/v1/knowledge/claims/972285MCP
get_claim(id=972285)