Question 1

What is the cost of Gemini-3.5-Flash-Lite by Poe?

Accepted Answer

Gemini-3.5-Flash-Lite by Poe costs $0.30 per 1M input tokens and $2.53 per 1M output tokens. Cached reads cost $0.03 per 1M tokens.

Question 2

What is the context window of Gemini-3.5-Flash-Lite by Poe?

Accepted Answer

Gemini-3.5-Flash-Lite by Poe has a context window of 1.0M tokens. It supports up to 1.0M input tokens and can generate up to 66K output tokens.

Question 3

What are the capabilities of Gemini-3.5-Flash-Lite by Poe?

Accepted Answer

Gemini-3.5-Flash-Lite by Poe supports advanced reasoning, tool calling/function calling, structured output, adjustable temperature, file attachments. It has closed weights.

Question 4

What input and output types does Gemini-3.5-Flash-Lite support?

Accepted Answer

Gemini-3.5-Flash-Lite by Poe accepts text, image, video, audio as input and can generate text as output.

Question 5

Does Gemini-3.5-Flash-Lite by Poe support reasoning?

Accepted Answer

Yes, Gemini-3.5-Flash-Lite by Poe supports advanced reasoning capabilities.

Question 6

Is Gemini-3.5-Flash-Lite by Poe open source?

Accepted Answer

No, Gemini-3.5-Flash-Lite by Poe has closed weights. The model is only available through the Poe API.

Question 7

Does Gemini-3.5-Flash-Lite support function calling?

Accepted Answer

Yes, Gemini-3.5-Flash-Lite by Poe supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

Question 8

What is the knowledge cutoff date for Gemini-3.5-Flash-Lite?

Accepted Answer

Gemini-3.5-Flash-Lite by Poe has a knowledge cutoff date of 2026-03. This means the model was trained on data available up until that date.

Gemini-3.5-Flash-Lite API

Input Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)

Output Modalities