Google

Gemini 2.0 Flash

Complete specs, pricing, and benchmark data for Gemini 2.0 Flash by Google. Last verified 2026-04-03.

VisionMultimodalJSON ModeFunctionsStreamingCode Exec
Pricing

Input / 1M tokens

$0.100

Output / 1M tokens

$0.400

Cached Input / 1M

$0.025

Context & Output

Context Window

1.048576M

Max Output

8,192

TTFT

120ms

Speed

160 tok/s

Benchmarks

Arena ELO

1260

Coding ELO

1240

Reasoning ELO

1230

HumanEval

88

MMLU

85.5

MATH

73.5

GPQA

52.8

Price History (Input $/M tokens)

Strengths
  • +Extremely fast inference
  • +1M context window at very low cost
  • +Strong multimodal support
  • +Great for real-time applications
Limitations
  • -Weaker reasoning than Pro models
  • -Smaller max output
  • -Less capable on complex tasks

Best For

ChatbotsHigh VolumeCost SensitiveMultimodal

Compare Gemini 2.0 Flash with...

Official Pricing Page →