name = "Google: Gemini 2.5 Flash Lite"
description = "Low-latency Gemini model for high-volume multimodal and agent workloads"
release_date = "2025-06-17"
last_updated = "2026-03-15"
attachment = true
reasoning_options = [{ type = "toggle" }, { type = "budget_tokens", min = 0, max = 24_576 }]
reasoning = true
temperature = true
tool_call = true
open_weights = false

[cost]
input = 0.1
output = 0.4
reasoning = 0.4
cache_read = 0.01
cache_write = 0.083333

[limit]
context = 1048576
output = 65535

[modalities]
input = ["audio", "image", "pdf", "text", "video"]
output = ["text"]