Unverified50% confidenceFactExact time
The output speed of traditional large models is typically between 50 and 150 tokens per second, while high-performance models such as Claude and GPT-4o can reach 200 to 400 tokens per second after optimization.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/8/2026
First Seen
Valid until: 12/7/2026
Sources
Related Entities
Related Claims
UnverifiedThe measured inference speed of running a 90-million-parameter model on a PSP is approximately 0.5 to 0.6 tokens per second, with a complete response taking 1 to 3 minutes to generate.68% similarUnverifiedChatGPT标准模式的输出速度通常在50-100 Token/秒左右67% similarUnverifiedClaude or GPT-4 may need 30 seconds or even longer when handling complex multi-file refactoring tasks66% similarUnverifiedProcessing a pair of long texts with GPT-4 takes approximately a few seconds and a few cents, and the output has randomness that requires temperature control and multiple sampling to improve stability.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/877300API
curl https://kongchang.com/api/v1/knowledge/claims/877300MCP
get_claim(id=877300)