Google models on Felo

Compare Google models currently available through Felo, including model IDs, published pricing, specifications, and capabilities.

Input types

Output types

4 / 4 Model

Google: Nano Banana Pro (Gemini 3 Pro Image)

Marketing visualsPoster typographyProduct mockups

Google DeepMind's flagship image model built on Gemini 3 Pro, known for legible multilingual text,4K output, and studio-grade conversational editing.

GoogleListed —131.072K Context$2/ 1M tokensInput tokens$12/ 1M tokensOutput tokens

Image · TextImage · Text

Google: Gemini 3.8 Flash

Up to 50% off

Agentic codingLong-horizon engineeringTool orchestration

Google's Gemini 3.8 Flash is a fast, cost-efficient workhorse model for agentic coding, multimodal understanding and long-horizon tool use, with a 1M-token context window.

GoogleListed —1.049M Context$1.5/ 1M tokensInput tokens$7.5/ 1M tokensOutput tokens

Text · Image · Video · File · AudioText

Google: Gemini 4 Argon

Up to 50% off

Codebase migrationVulnerability patchingFinance research

Google's flagship Gemini 4 model with a unified 1M-token context window and up to 1M-token output, built for long-horizon software engineering, enterprise knowledge work, and cyber defense.

GoogleListed —1.049M Context$4/ 1M tokensInput tokens$20/ 1M tokensOutput tokens

Audio · File · Image · Text · VideoText

Google: Nano Banana 2.1

InfographicsPosters and adsMasked local edits

Google DeepMind's efficient image generation and editing model built on Gemini 3.6 Flash, with 4K output, masked local edits, and multi-reference subject consistency.

GoogleListed —65.536K Context$1.5/ 1M tokensInput tokens$7.5/ 1M tokensOutput tokens

Image · TextImage · Text