Gemini 1.5 Pro
Available frontierGoogle's flagship model with 2M token context window
Released February 15, 2024
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
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
Other Google AI Models
See all models- Gemini 2.0 Flash
- Google's fastest multimodal model with native tool use
- Context
- 1M
- Speed
- N/A
- TTFT
- N/A
- Gemini 2.0 Flash Thinking
- Experimental reasoning model with transparent thought process
- Context
- 1M
- Speed
- N/A
- TTFT
- N/A
- Gemini 1.5 Flash
- Fast, efficient multimodal model for high-volume tasks
- Context
- 1M
- Speed
- N/A
- TTFT
- N/A
Get the signal, skip the noise.
Weekly digest of new models and provider updates across 41+ compute providers. Curated for AI builders who ship.