Gemini 3.6 Flash

Gemini 3.6 Flash is Google's high-efficiency workhorse model, tuned for coding, agentic workflows, and web and app development. Built on Gemini 3.5 Flash, it aims for polished output with fewer unnecessary edits and less hedging, spending roughly 17% fewer output tokens and fewer tool calls to finish the same multi-step task. It accepts text, images, audio, video, and PDFs across a 1M-token context window and returns up to 64K tokens of text, with configurable reasoning effort, structured output, and tool use.

Google: Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite is Google's GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.

Google: Gemini 3.1 Flash Lite Preview

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Delivers 2.5x faster Time to First Answer Token and 45% increased output speed compared to 2.5 Flash. Priced at half the cost of Gemini 3 Flash.

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google's frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows. Designed for advanced development and agentic systems, it introduces a new medium thinking level to better balance cost, speed, and performance.

Gemini 2.5 Flash Lite Preview 06-17

Gemini 2.5 Flash Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

Gemini 2.5 Flash Preview 05-20

Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Note: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the ":thinking" suffix), the model will explicitly avoid generating thinking tokens. To utilize the thinking capability and receive thinking tokens, you must choose the ":thinking" variant, which will then incur the higher thinking-output pricing. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter.

Gemini 3.6 Flash

Gemini 3.6 Flash is Google's high-efficiency workhorse model, tuned for coding, agentic workflows, and web and app development. Built on Gemini 3.5 Flash, it aims for polished output with fewer unnecessary edits and less hedging, spending roughly 17% fewer output tokens and fewer tool calls to finish the same multi-step task. It accepts text, images, audio, video, and PDFs across a 1M-token context window and returns up to 64K tokens of text, with configurable reasoning effort, structured output, and tool use.

Google: Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite is Google's GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.

Google: Gemini 3.1 Flash Lite Preview

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Delivers 2.5x faster Time to First Answer Token and 45% increased output speed compared to 2.5 Flash. Priced at half the cost of Gemini 3 Flash.

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google's frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows. Designed for advanced development and agentic systems, it introduces a new medium thinking level to better balance cost, speed, and performance.

Gemini 2.5 Flash Lite Preview 06-17

Gemini 2.5 Flash Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

Gemini 2.5 Flash Preview 05-20

Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Note: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the ":thinking" suffix), the model will explicitly avoid generating thinking tokens. To utilize the thinking capability and receive thinking tokens, you must choose the ":thinking" variant, which will then incur the higher thinking-output pricing. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter.