Unverified50% confidenceBenchmarkExact time
OpenAI GPT-4o's API response speed is typically around 80–100 T/s.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/1/2026
First Seen
Valid until: 11/30/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI's GPT-4o API typically achieves 50–100 tokens/second, and Claude's streaming output also falls in the range of 30–80 tokens/second.78% similarVerifiedOpenAI previewed an Ultra Fast speed service mode in the API, enabling GPT-5.6 to achieve up to a 14x speed improvement with an output throughput of 750 tokens per second.77% similarUnverifiedSince 2023, OpenAI has adjusted the input/output token unit prices for the GPT-4 series multiple times, with the largest reduction exceeding 80%.77% similarUnverifiedGPT-5.5's response speed is noticeably faster than Opus 4.7, and the team attributes this to OpenAI's hardware advantage.76% similarUnverified主流商业模型如GPT-4o的输出速度通常在50-100 TPS区间75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/837547API
curl https://kongchang.com/api/v1/knowledge/claims/837547MCP
get_claim(id=837547)