Choose from the models that matter.

Low-latency Gemini model for high-volume multimodal and agent workloads

Context

1,050,000

Providers

10

Input / 1M

$0.25

Output / 1M

$1.5

Reasoning-first Gemini preview for agentic coding and complex problem solving

Context

1,048,756

Providers

21

Input / 1M

$2

Output / 1M

$12

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Context

1,048,756

Providers

8

Input / 1M

$2

Output / 1M

$12

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Context

1,048,576

Providers

22

Input / 1M

$0.1857

Output / 1M

$1.1142

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Context

1,048,756

Providers

21

Input / 1M

$0.07

Output / 1M

$0.43

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Context

1,048,576

Providers

10

Input / 1M

$0.57

Output / 1M

$3.43

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Context

8,192

Providers

3

Input / 1M

$0.15

Output / 1M

$0

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Context

1,048,756

Providers

7

Input / 1M

$1.5

Output / 1M

$9

Low-latency Gemini model for high-volume multimodal and agent workloads

Context

1,048,576

Providers

5

Input / 1M

$0.25

Output / 1M

$1.5

Video generation and editing model for fast, conversational text- and image-to-video workflows

Context

1,048,576

Providers

2

Input / 1M

$1.5

Output / 1M

$9

Open Gemma instruction model for efficient chat and self-hosted deployments

Context

262,144

Providers

14

Input / 1M

$0.06

Output / 1M

$0.33

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Context

262,144

Providers

25

Input / 1M

$0

Output / 1M

$0