Google / google/gemini-3.5-flash-lite

Gemini 3.5 Flash-Lite - access through LLMTR

Positioned for work where latency and cost are the binding constraints: bulk document parsing, data extraction, translation, classification, and subagent tasks. It offers 1M context, 65K output, image/video/audio/PDF input, and tool calling at a token price well below the Flash tier, and can be pushed faster by lowering the thinking level to minimal.

Technical specifications

Canonical IDgoogle/gemini-3.5-flash-lite
ProviderGoogle
Context window1,048,576 tokens
OperationsCHAT_COMPLETIONS, RESPONSES
Modalitiesimage, video, audio, text

Pricing

A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$2.50
CHAT_COMPLETIONSINPUT_AUDIOPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSINPUT_IMAGEPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSINPUT_VIDEOPER_1M_TOKENS$0.300000
CHAT_COMPLETIONSTOOL_CALLPER_1K_CALLS$14.00
CHAT_COMPLETIONSTOOL_CALLPER_1K_CALLS$14.00

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.5-flash-lite","messages":[{"role":"user","content":"Hello"}]}'

Related models