LLMversus
Google

Gemini 2.5 Pro

Complete specs, pricing, and benchmark data for Gemini 2.5 Pro by Google. Last verified 2026-04-20.

VisionMultimodalJSON ModeFunctionsStreamingCode Exec
Pricing

Input / 1M tokens

$1.25

Output / 1M tokens

$10.00

Cached Input / 1M

$0.125

Context & Output

Context Window

1.048576M

Max Output

65,536

TTFT

400ms

Speed

70 tok/s

Benchmarks

Arena ELO

1430

Coding ELO

1430

Reasoning ELO

1430

HumanEval

94

MMLU

92

MATH

90.5

GPQA

74

Try Gemini 2.5 Pro API

Start building with Gemini 2.5 Pro

Get API Access→

Price History (Input $/M tokens)

Strengths
  • +1M token context window
  • +Excellent reasoning capabilities
  • +Strong coding performance
  • +Native multimodal support
Limitations
  • -Higher output pricing tier
  • -Variable latency on long contexts
  • -Google ecosystem lock-in concerns

Best For

CodingReasoningLong ContextMultimodal

Compare Gemini 2.5 Pro with...

vs Claude Opus 4vs o3vs DeepSeek R1vs o1vs Qwen 3 235B MoEvs Gemini Experimental 1206vs GPT-4.5vs DeepSeek R1 (Groq)vs Llama 4 Maverickvs DeepSeek R1 (Together)vs Grok 3vs Claude Sonnet 4
Official Pricing Page →
Your ad here