Agent Mag
SUBSCRIBE
Gemini 2.5 Pro
All models
GoogleGoogleGeminiReleased June 17, 2025

Gemini 2.5 Pro

1.0M context$1.25/M input$10.00/M output

Gemini 2.5 Pro is Google's advanced AI model designed for tasks requiring high-level reasoning, coding, mathematics, and scientific analysis. It incorporates enhanced 'thinking' capabilities for nuanced context handling and accurate responses. The model has achieved top-tier performance on benchmarks, including first-place rankings on the LMArena leaderboard, showcasing its alignment with human preferences and ability to solve complex problems.

What is Gemini 2.5 Pro?

Gemini 2.5 Pro is an AI model from Google that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Gemini 2.5 Pro against other models for agent workflows and production deployments.

Model ID

Gemini 2.5 Pro is Google's advanced AI model designed for tasks requiring high-level reasoning, coding, mathematics, and scientific analysis. It incorporates enhanced 'thinking' capabilities for nuanced context handling and accurate responses. The model has achieved top-tier performance on benchmarks, including first-place rankings on the LMArena leaderboard, showcasing its alignment with human preferences and ability to solve complex problems.

Architecture & Specifications
Tokenizer
Gemini
Training Data
Knowledge cutoff January 31, 2025
License
Proprietary
Released
June 17, 2025
Modalities
Input
textimagefileaudiovideo
Output
text
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Strengths
  • Advanced reasoning capabilities
  • Top-tier performance on benchmarks
  • Nuanced context handling
  • Human-preference alignment
  • Complex problem-solving abilities
Limitations
  • Structured output error rates vary across providers
  • Tool call error rates are higher for certain providers
  • Latency differences across providers
Recommended Use Cases
Scientific research and analysis
Advanced coding and software development
Mathematical problem solving
Legal and financial reasoning
Marketing and content creation

More from Google

Gemma 4 26B A4B
262K ctx$0.060/M

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B (free)
262K ctxFree

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 31B
262K ctx$0.130/M

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 26B A4B (free)
262K ctxFree

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Related content

Browse the AI models directory

Compare pricing, local installs, context windows, and modality filters across the full model catalog.

Explore AI agent tools

Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.

Read Agent Mag model and agent articles

See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.

Data enriched Apr 24, 2026. Pricing from OpenRouter API.