AI Gateway Benchmark: Prompt Injection Defense
码农暖爸@Delroy715
2:13This project benchmarks TypeSafe Jev against gemini-3.8-flash for prompt injection defense, highlighting Jev's significantly lower latency and transaction cost.
📊 AI Gateway Benchmark: Prompt Injection Defense
🔬 TypeSafe Jev (System 1) vs gemini-3.8-flash
⚡ Latency (端到端延迟):
• Jev: 1435 ms [14.3x Faster]
• gemini-3.8-flash: 20585 ms
💰 Transaction Cost (单次调用成本):
• Jev: $0.000027 (Input $0.042/M, Output 0 Token Free)
• gemini-3.8-flash: $0.001273 [47x Cost Reduction]
🛡️ Architectural Advantage:
• Jev: Direct logit probability estimation · Zero token generation · No JSON truncation
• LLM: Tokens: 197 in / 300 out (217 reasoning) · Autoregressive latency overhead
#TypeSafeAI #Jev