API
3 articles
-
OpenAIOpenAI's Decisions API Is Fast and Overconfident
OpenAI opened the Decisions API to all developers on 6 October: POST /v1/decisions on gpt-6-luna returns a probability, a choice or a score 'about 10x faster than the Responses API' at $0.10 per million input tokens with no output or cache charges. A forum tester ran a 70%-heads coin through it: the predicate returned 70% over 1,000 trials, the choice format returned heads 98% of the time and moved when options were reordered. The guide never defines its confidence field or mentions calibration. With no caching, a classifier with a 4,000-token rubric costs about five times more here than Luna through Responses; the endpoint only wins when output exceeds 18% of the cached prefix.
-
GeminiGemini 3.7 Flash Is Deprecated and Quietly Swapped Out
On 8 October Google deprecated gemini-3.7-flash, a stable model released on 13 August, and gemini-3.5-flash, with no shutdown date for either. Requests to both IDs now return 200 and are silently served by 3.8 Flash and 3.6 Flash; the model list and metadata endpoint show no change, and the only signal is the modelVersion field in the response. Vertex AI gives the same model a fixed retirement date instead. Log modelVersion and re-run your evals.
-
EngineeringPrompt Caching Decides Whether an AI Product Survives
Claude Code treats prompt cache misses like server outages. The engineering behind that decision saves millions in API costs.