Gemini 3.1 Flash-Lite (Preview)
by Google · chat
Frontier-class performance rivaling larger models at a fraction of the cost.
Pricing
Input: $0.2375/M tokens · Output:
by Google · chat
Frontier-class performance rivaling larger models at a fraction of the cost.
Input: $0.2375/M tokens · Output:
.425/M tokens
Vision, Function Calling, JSON Mode, Streaming, Reasoning
Context: 1049K tokens
Max output: 8K tokens
Routes: 1/1 healthy
TTFT: 332ms · Latency: 2216ms · Throughput: 2.4 tok/s