GPT-5.4 and GPT-5.4 Mini have been retired · Please switch to another available model
All models
Google · APINew

Gemini 3.5 Flash-Lite API

Use 1M context with one OmniaKey API key.

Model ID
gemini-3.5-flash-lite
Context
1M
Provider
Google
Input · USD / 1M tokens
$0.24 USD
Official price $0.3 USD
Output · USD / 1M tokens
$2 USD
Official price $2.5 USD
Savings
20%
Last verified
2026-07-22

01

Where it fits

Choose it for high-volume agent loops where the bill matters more than maximum reasoning depth.

02

Model capabilities

Vision

Accepts visual input alongside text for multimodal coding and analysis tasks.

Tool use

Can select and call tools in agent workflows that support structured tool use.

Fast responses

Optimized for responsive iteration and higher-volume agent tasks.

03

OpenAI-compatible API

Keep your client and change the base URL, API key, and model ID.

curl
curl https://api.omniakey.com/v1/chat/completions \
  -H "Authorization: Bearer $OMNIAKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash-lite",
    "messages": [{"role": "user", "content": "Explain this codebase"}],
    "stream": true
  }'

04

Compatible coding tools

Cursor
Cline
Aider

More Google models

Frequently asked questions

How much does Gemini 3.5 Flash-Lite cost on OmniaKey?

OmniaKey charges $0.24 USD per 1M input tokens and $2 USD per 1M output tokens, in USD. Official prices are $0.3 USD and $2.5 USD; you save 20%.

What is the context window for Gemini 3.5 Flash-Lite?

The listed context window is 1M. Actual usable limits can also depend on the client and upstream request format.

Which coding tools work with Gemini 3.5 Flash-Lite?

The current catalog lists compatibility with Cursor, Cline, Aider. Use the model ID shown on this page when the client supports model selection.

Gemini 3.5 Flash-Lite API, Pricing & Coding Guide · OmniaKey