{"$k":["slug","chart"],"$r":[["cli-model-latency-tokens",{"id":"cli-vs-api-exact-reply-latency","title":"CLI vs API: time for a one-line answer","subtitle":"Matched cohort, fixed exact reply, 5 runs per configuration","kind":"dot-range","unit":"seconds","yLabel":"Seconds","series":[{"name":"Total time","points":{"$k":["label","value","lo","hi","n"],"$r":[["OpenAI API · GPT-6 Luna · none",0.97,0.65,1.5,5],["OpenAI API · GPT-6.1 Sol · low",1.02,0.96,1.87,5],["OpenAI API · GPT-6.1 Sol · high",1.52,1.35,2.23,5],["Codex CLI · GPT-6 Luna · none",3.19,2.88,3.83,5],["Codex CLI · GPT-6.1 Sol · low",4.18,3.86,4.53,5],["Codex CLI · GPT-6.1 Sol · high",4.19,3.81,4.69,5]]}},{"name":"First useful output","points":{"$k":["label","value","lo","hi","n"],"$r":[["OpenAI API · GPT-6 Luna · none",0.82,0.51,1.37,5],["OpenAI API · GPT-6.1 Sol · low",0.87,0.84,1.74,5],["OpenAI API · GPT-6.1 Sol · high",1.34,1.26,2.12,5],["Codex CLI · GPT-6 Luna · none",2.79,2.46,3.42,5],["Codex CLI · GPT-6.1 Sol · low",3.75,3.44,4.1,5],["Codex CLI · GPT-6.1 Sol · high",3.79,3.37,4.3,5]]}}],"note":"Dot = median; whiskers = fastest and slowest run (a range, not a confidence interval). Every run in these cohorts passed its validator.","sourceIds":["agent-provider-explorer"]}],["cli-model-latency-tokens",{"id":"cli-vs-api-small-coding-latency","title":"CLI vs API: time for a small coding task","subtitle":"Matched cohort, small coding task, 3 runs per configuration","kind":"dot-range","unit":"seconds","yLabel":"Seconds","series":[{"name":"Total time","points":{"$k":["label","value","lo","hi","n"],"$r":[["OpenAI API · GPT-6 Luna · none",4.01,3.83,4.35,3],["OpenAI API · GPT-6.1 Sol · low",6,5.44,6.2,3],["Codex CLI · GPT-6 Luna · none",9.23,8.99,11.68,3],["OpenAI API · GPT-6.1 Sol · high",9.56,9.44,10.94,3],["Codex CLI · GPT-6.1 Sol · low",14.15,13.02,14.41,3],["Codex CLI · GPT-6.1 Sol · high",17.85,17.68,22.42,3]]}},{"name":"First useful output","points":{"$k":["label","value","lo","hi","n"],"$r":[["OpenAI API · GPT-6 Luna · none",0.67,0.62,0.81,3],["OpenAI API · GPT-6.1 Sol · low",1.05,0.97,1.4,3],["Codex CLI · GPT-6 Luna · none",8.68,8.27,11.01,3],["OpenAI API · GPT-6.1 Sol · high",5.31,4.99,6.42,3],["Codex CLI · GPT-6.1 Sol · low",13.6,12.52,13.83,3],["Codex CLI · GPT-6.1 Sol · high",17.27,17.13,21.86,3]]}}],"note":"Dot = median; whiskers = fastest and slowest run (a range, not a confidence interval). Every run in these cohorts passed its validator.","sourceIds":["agent-provider-explorer"]}],["cli-model-latency-tokens",{"id":"cli-vs-api-prompt-overhead","title":"Hidden prompt: input tokens for the same one-line request","subtitle":"Reported input tokens, matched cohort","kind":"bar","unit":"tokens","yLabel":"Input tokens per call","series":[{"name":"Input tokens","points":{"$k":["label","value","n"],"$r":[["OpenAI API · GPT-6 Luna · none",17,5],["OpenAI API · GPT-6.1 Sol · low",17,5],["OpenAI API · GPT-6.1 Sol · high",17,5],["Codex CLI · GPT-6 Luna · none",18859,5],["Codex CLI · GPT-6.1 Sol · low",19551,5],["Codex CLI · GPT-6.1 Sol · high",19555,5]]}}],"note":"The CLI wraps every request in its own system prompt and tool context; the bare API sends only the request. Part of the CLI input is served from cache.","sourceIds":["agent-provider-explorer"]}]]}