Google · Small and fast

Gemini 3.5 Flash-Lite API pricing and specs

Google's low-cost model, which Google suggests as the subagent in multi-agent setups.

Input

⁨$0.30⁩

Cached input

⁨$0.030⁩

Output

⁨$2.50⁩

US dollars per million tokens, standard tier, short-prompt rate

Text, image, video and audio input all cost the same per token. Computer use is available in preview.

Spec sheet

API model string: gemini-3.5-flash-lite
Provider: Google
Context: 1.05M tokens
Max output: 66K tokens
Released: July 21, 2026
Batch API: 50% off, results within hours
Documented agent features: Tool callingStructured outputComputer useBuilt-in web searchAdjustable reasoning

What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

Workload	Per task	Per 1,000 tasks
Support bot 4 calls, short tool lookups	⁨$0.011⁩	⁨$11⁩
Coding agent 30 calls, files and test output	⁨$0.333⁩	⁨$333⁩
Browser agent 25 calls, screenshots and page text	⁨$0.219⁩	⁨$219⁩
Research agent 15 calls, long search results	⁨$0.221⁩	⁨$221⁩