Nano Banana 2 (gemini-3.1-flash-image) is Google's speed-oriented image generation and editing model, accepting text and image input and returning generated images.

gemini-3.1-flash-image

Defines the width-to-height proportion for generated visual output.

gemini-4-argon

Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

Focuses on the most likely words based on a percentage of probability.

If true, returns the log probabilities of each output token returned in the content of message.

This parameter tells the model to stop generating text when it reaches any of the specified sequences (like a word or punctuation)

Lists tool definitions or capabilities available to the model.

Decides whether to use tools or just the model for generating responses.

Defines the format or type of the generated response.

Enables parallel execution of tools, allowing multiple tools to run simultaneously.

Sends the response in real-time as it's being generated.

Gemini 3.1 Flash-Lite is a fast, cost-effective multimodal model in the Gemini 3.1 family, positioned as the lightweight option for high-throughput, low-latency workloads.

gemini-3.1-flash-lite

Controls the level of thinking/reasoning used by the model.

Gemini Omni Flash generates and edits video from text, image, and video inputs with natural-language multi-turn refinement.

gemini-omni-1.1-flash

Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows, with the speed and cost efficiency of Flash. Supports text, image, video, audio, and PDF input with a 1,048,576-token input limit and 65,536-token output limit..

gemini-3.8-flash

Controls the level of reasoning (thinking) used by the model. Minimal is not supported and returns an error for this model.

Selects Standard, Priority, or Flex inference consumption option.

Gemini 3.7 Flash is Google's fast, cost-efficient multimodal model released August 2026, featuring a 1M-token context window, tunable thinking (reasoning) levels, and improved coding and agentic performance over Gemini 3.6 Flash.

gemini-3.7-flash

Controls the level of reasoning (thinking) used by the model.

Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing. Ideal for high-volume agentic workflows and simple data extraction. Released July 21, 2026.

gemini-3.5-flash-lite

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at higher speed and lower cost. Designed for the agentic era, it excels at code generation, agentic execution, and spatial reasoning. Released July 21, 2026.

gemini-3.6-flash

Newest and most capable Speed oriented Frontier model from Google.

gemini-3.5-flash

Gemini 3 Flash combines Gemini 3 Pro's reasoning capabilities with the Flash line's levels on latency, efficiency, and cost

gemini-3-flash-preview

Gemini 3.1 Pro is our most advanced reasoning Gemini model, capable of solving complex problems.

gemini-3.1-pro-preview

Controls the level of reasoning used by the model.

The most cost-efficient and fastest model in the 2.5 family, optimized for extreme low-latency and high-throughput scenarios.

gemini-2.5-flash-lite

state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

gemini-2.5-pro

best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.

gemini-2.5-flash

Nano Banana 2 Lite (gemini-3.1-flash-lite-image) is Google's ultra-low-latency, cost-effective image generation and editing model, designed for high-volume interactive use cases. Accepts text, image, video and PDF input and returns generated images and text.

gemini-3.1-flash-lite-image

Nano Banana Pro (gemini-3-pro-image) is Google's highest-quality image generation and editing model, supporting 1K/2K and 4K output.

Model	Context	Max output	Input	Output	Capabilities
gemini-4-argon Chat	1.0M	66K	$2.00	$10.00	Files, Tools, System prompt
gemini-3.1-flash-lite Chat	1.0M	66K	$0.25	$1.50	Vision, Files, Tools, System prompt, Reasoning
gemini-omni-1.1-flash Chat	1.0M	66K	$1.50	$9.00	Vision, Files, System prompt
gemini-3.8-flash Chat	1.0M	66K	$0.75	$3.75	Vision, Files, Tools, System prompt, Reasoning
gemini-3.7-flash Chat	1.0M	66K	$0.75	$3.75	Vision, Files, Tools, System prompt, Reasoning
gemini-3.5-flash-lite Chat	1.0M	66K	$0.30	$2.50	Vision, Files, Tools, System prompt, Reasoning
gemini-3.6-flash Chat	1.0M	66K	$0.75	$3.75	Vision, Files, Tools, System prompt, Reasoning
gemini-3.5-flash Chat	1.0M	66K	$1.50	$9.00	Vision, Tools, System prompt
gemini-3-flash-preview Chat	1.0M	66K	$0.50	$3.00	Vision, Tools, System prompt
gemini-3.1-pro-preview Chat	1.0M	66K	$2.00	$12.00	Vision, Tools, System prompt, Reasoning
gemini-2.5-flash-lite Chat	1.0M	66K	$0.10	$0.40	Vision, Tools, System prompt
gemini-2.5-pro Chat	1.0M	66K	$1.25	$10.00	Vision, Tools, System prompt
gemini-2.5-flash Chat	1.0M	66K	$0.30	$2.50	Files, Tools, System prompt
gemini-3.1-flash-lite-image Image	—	—	—	—	Vision
gemini-3-pro-image Image	—	—	—	—	Vision

gemini-3.1-flash-image

Start building today