Google AI

Gemini 1.5 Pro

Available frontier

Google's flagship model with 2M token context window

Released February 15, 2024

Context Window
2M
TTFT
N/A
Speed
N/A
Max Output
8K
Training Cutoff
Nov 2023

Last tested: 2026-01-15

About

Gemini 1.5 Pro is Google's most capable production model, featuring an industry-leading 2 million token context window. It excels at long-document analysis, complex reasoning, and multimodal understanding. The model can process hours of video, extensive codebases, or lengthy documents in a single context.

Capabilities

vision audio video function-calling streaming code-execution json-mode

Pricing

Input
$1.25/M
per 1M tokens
Output
$5.00/M
per 1M tokens

Static pricing

Details

Overview

Gemini 1.5 Pro represents a major architectural advancement in large language models, introducing Google’s Mixture-of-Experts (MoE) approach that enables unprecedented context lengths without sacrificing quality. With a 2 million token context window, it can process entire codebases, full-length books, or hours of video content.

Key Features

Massive Context Window

The 2M token context window enables use cases previously impossible with traditional LLMs:

  • Analyze entire repositories in one prompt
  • Process multi-hour meeting recordings
  • Review complete legal document sets
  • Study full research paper collections

True Multimodal Understanding

Gemini 1.5 Pro natively understands text, images, audio, and video, enabling seamless cross-modal reasoning and analysis.

High Recall Across Context

The model maintains strong recall even at extreme context lengths, successfully retrieving information embedded anywhere in the input with “needle in a haystack” accuracy above 99%.

Benchmark Performance

Gemini 1.5 Pro achieves state-of-the-art results across multiple benchmarks:

  • MMLU: 85.9% (5-shot)
  • HumanEval: 84.1% code generation
  • MATH: 67.7% mathematical reasoning
  • Long-context retrieval: 99.7% accuracy at 1M tokens

Use Cases

  • Code Analysis: Review entire codebases for bugs, patterns, or architecture issues
  • Document Intelligence: Process and analyze large document collections
  • Video Understanding: Extract insights from long-form video content
  • Research: Analyze multiple papers and synthesize findings
  • Meeting Analysis: Transcribe and summarize extended recordings

Pricing Tiers

Gemini 1.5 Pro offers tiered pricing based on context length:

  • Up to 128K tokens: $1.25/M input, $5.00/M output
  • Over 128K tokens: $2.50/M input, $10.00/M output

Best Practices

  • Use the full context window for complex analysis tasks
  • Combine with function calling for agentic workflows
  • Leverage multimodal inputs for richer understanding
  • Consider Gemini 1.5 Flash for simpler, latency-sensitive tasks
Newsletter

Get the signal, skip the noise.

Weekly digest of new models and provider updates across 41+ compute providers. Curated for AI builders who ship.

New model releases
Capability updates
Provider status
bots.so
The AI Inference Model Index
© bots.so — The AI Inference Model Index

bots.so aggregates publicly available model deployment information from official provider sources. We are not affiliated with any model provider. Model availability changes rapidly; always verify on official sites.