Unverified50% confidenceFactExact time
In computer use, the system prompt adds 466–499 tokens, each tool definition adds 735 tokens, and each screenshot consumes roughly 2,000–5,000 tokens.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedA log study measured the tokens each harness sends before reading the user's prompt: OpenCode approximately 7,000 tokens, CloudCode approximately 33,000 tokens, and Pi approximately 1,300 tokens.74% similarUnverifiedThe same code refactoring task may consume 3,000 tokens in standard mode and may balloon to over 50,000 tokens in Extra High mode.73% similarUnverifiedThe hosted-side usage across the 400 cases totals 1,222,211 tokens (290,606 input, 931,605 output), i.e. 3,055.5 tokens per case.73% similarUnverifiedReal-world testing with the 284-billion-parameter DeepSeek V4 Flash shows token generation rising from 37 to 53 tokens/s (approximately 1.5x), and Prompt Processing jumping from 483 to 1,485 tokens/s (approximately three times).73% similarUnverifiedThe embedding model's maximum length means that inputs exceeding 512 tokens are silently truncated, so the example sets the chunk budget to 480 tokens.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057370API
curl https://kongchang.com/api/v1/knowledge/claims/1057370MCP
get_claim(id=1057370)