Unverified50% confidenceBenchmarkExact time
Typing '你好' in Pi consumes approximately 1,100 upload tokens, whereas saying hello in Codex consumes 18,000 tokens (approximately 7% of the context window).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
VerifiedLarge model APIs are typically billed by the number of Tokens, with approximately every 750 English words or 400 Chinese characters corresponding to 1,000 Tokens.66% similarPartially VerifiedTencent Hunyuan API costs approximately 1.5 CNY per million tokens for input and approximately 5 CNY per million tokens for output.63% similarUnverifiedWhen the oh-my-openagent plugin is enabled, token consumption is approximately 39,000 tokens; with it disabled, approximately 20,000 tokens — enabling the plugin nearly doubles consumption.62% similarUnverifiedA token roughly corresponds to 0.75 English words or approximately 1.5 Chinese characters, and the API call cost for GPT-4-level models is typically in the range of a few to tens of dollars per million tokens.61% similarUnverifiedIn high-frequency development scenarios, if each conversation carries 2,000–5,000 tokens of specification instructions, 50 calls per day would consume an additional 100,000–250,000 tokens.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908958API
curl https://kongchang.com/api/v1/knowledge/claims/908958MCP
get_claim(id=908958)