Every model.One place.

Google's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.

Model ID

google/gemini-4-argon

Discovery tier

Frontier

Context window

1,048,576 tokens

Compatibility alias that routes to the newest version of Gemini Pro. Currently routes to Gemini 3.1 Pro Preview High.

Model ID

google/gemini-pro-latest

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 3.1 Pro preview variant tuned for better tool selection behavior in coding agents and multi-tool workflows. It reduces overuse of generic bash tools and improves function-calling reliability while retaining Gemini 3.1 Pro's multimodal reasoning and 1M-token context. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

Model ID

google/gemini-3.1-pro-preview-customtools

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 3.1 Pro preview high-reasoning variant.

Model ID

google/gemini-3.1-pro-preview-high

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 3.1 Pro preview low-reasoning variant.

Model ID

google/gemini-3.1-pro-preview-low

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 3.1 Pro preview is built for tasks where simple answers are not enough. Stronger core reasoning for complex coding, math, and long-context workflows, with multimodal support and a reported 77.1% verified score on ARC-AGI-2. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

Model ID

google/gemini-3.1-pro-preview

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 2.5 Pro stable release. Google's most capable generalist model with strong performance across a wide range of tasks.

Model ID

gemini-2.5-pro

Discovery tier

Frontier

Context window

1,048,576 tokens

Gemini 3 Pro with native image generation support. Can generate images inline from text prompts.

Model ID

gemini-3-pro-image-preview

Discovery tier

Balanced

Context window

65,536 tokens

Note: This preview is mapped to Gemini 2.5 Pro (stable).

Model ID

gemini-2.5-pro-preview-06-05

Discovery tier

Balanced

Context window

1,048,576 tokens

Gemini 2.5 Pro Preview 0506. Google's model from May 2025.

Model ID

gemini-2.5-pro-preview-05-06

Discovery tier

Balanced

Context window

1,048,576 tokens

Gemini 2.5 Pro Exp 0325. Google's experimental model from March 2025.

Model ID

gemini-2.5-pro-exp-03-25

Discovery tier

Balanced

Context window

1,048,576 tokens

Gemini 2.5 Pro Preview 0325. Google's model from March 2025.

Model ID

gemini-2.5-pro-preview-03-25

Discovery tier

Balanced

Context window

1,048,576 tokens

Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement.

Model ID

gemini-2.0-pro-exp-02-05

Discovery tier

Balanced

Context window

2,097,152 tokens

Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement.

Model ID

gemini-exp-1206

Discovery tier

Balanced

Context window

2,097,152 tokens

Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement. 'DeepGemini', fusion of Gemini 2.5 Pro and Deepseek R1.

Model ID

gemini-2.0-pro-reasoner

Discovery tier

Balanced

Context window

128,000 tokens

Google's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.

Model ID

google/gemini-3.8-flash

Discovery tier

Efficient

Context window

1,048,576 tokens

Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.

Model ID

google/gemini-3.7-flash

Discovery tier

Efficient

Context window

1,048,576 tokens

Google's cost-efficient Gemini 3.5 Flash Lite model for high-volume multimodal reasoning, tool use, and structured-output workloads.

Model ID

google/gemini-3.5-flash-lite

Discovery tier

Efficient

Context window

1,048,576 tokens

Google's GA Flash model delivers near-Pro coding and agentic capability at Flash-tier speed and cost, with improved token efficiency over Gemini 3.5 Flash. It is optimized for multi-step orchestration, full-stack code refactoring, general reasoning, and multimodal workflows.

Model ID

google/gemini-3.6-flash

Discovery tier

Efficient

Context window

1,048,576 tokens

Google's speed-focused Gemini Flash model for frontier multimodal intelligence across text, images, audio, video, PDFs, and code. Built for agentic coding, reliable tool use, structured outputs, and long-context workflows. Audio input costs $3.00 per million audio tokens.

Model ID

google/gemini-3.5-flash

Discovery tier

Efficient

Context window

1,048,576 tokens