Expired50% confidenceFactExact time
OpenAI'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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
The Complete Guide to Running GLM-5.2 Locally with 4 RTX 3090s for $4,000
bilibili程序员-智能译站6/24/2026
Related Claims
UnverifiedOpenAI will run GPT-5.6 Sol on the Cerebras platform at speeds of up to 750 tokens per second.75% similarUnverifiedEach tool description in GPT-4 typically consumes 200-500 Tokens.73% similarVerifiedFor OpenAI paid users at the Tier 1 level, the RPM limit for GPT-4 is only 500 requests per minute.73% similarUnverifiedMainstream large model APIs such as OpenAI GPT-4o and Anthropic Claude both use a per-token billing model, with input and output tokens priced separately.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40846API
curl https://kongchang.com/api/v1/knowledge/claims/40846MCP
get_claim(id=40846)