Gemini 2.5 Pro
google/gemini-2.5-pro- Family · Gemini 2 Pro
- Released 5 Jun 2025
- Text · Image · File · Audio · Video → Text
- Tools · JSON · Vision
Spec & list price
Context1M
Max output64K
Input / 1M$1.25
Output / 1M$10.008× input
Scores · standing
Intelligence16.1#168/490
Coding33.3#105/196
Usage
Tokens / day4.0B▼ 0.4% 7d
Usage rank#127
Requests / day406.0K
Tool calls / req0.02
Per request · 30 days
Avg input9.3K0.6× median
Avg output1.4K2.0× median
Cache hit46%0.7× median
Reasoning share60%about median
Tool-call failures5.6%3.0× median
Consumption
Peak 9.9B 29 SepLow 2.4B 31 OctRank today #127
News & trends
8 mentions this week ▲ 167%this model · videos, posts, articles · 30 days
Trending · 14 days
- Retrieval Augmented Generation on Apple Shortcuts - Gemini 2.5 Pro61 views
- La misma frase con cuatro voces de IA: TTS Maker, Gemini 2.5 Pro de Google, Hume y Fish Audio.1.2K views
News · latest from Google
- Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v529 Oct
- Gemini 4 Carbon (High) Scores 59 on Artificial Analysis v528 Oct
- Gemini 4 Carbonblog.google · 28 Oct
- Gemini 4 Carbon: Our next frontier modelGoogle DeepMind · 28 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 3 providers, latest day
Output speed#124/33477 tok/s1.2× faster than median
Fastest provider83 tok/sbest of 3 providers
First token#2853.15 s2.9× longer than median
#16 cheapest of 17 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases16.1
Technical details
- Tokenizer
- Gemini
- Knowledge cutoff
- 2025-01-31
- Moderation
- none
Request parameters 10
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- max_tokens
- seed
Interesting facts
- Less output room than similar models (65.5K against a 131.1K median).
- Released 515 days ago, the newest of 3 Gemini 2 Pro models.
When to use
Best for
- Hard math and science reasoning
- Code generation and review
- Long document and video understanding
- Multimodal analysis of files, audio and images
Think twice for
- Low-cost high-volume chat (Flash tiers cost less)
- Self-hosting (closed weights)
- Image generation
Research papers
- Structured Security Explanations for Learning-Based Vulnerability Detection27 Oct
- AudioRSI: Recursively Self-Improving Audio Reasoners27 Oct
- Retrospective Comparison of Radiation Oncology Patient Message Responses Generated by Epic and Institutionally Managed LLMs25 Oct
- Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance23 Oct
- REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming11 Oct
- AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning9 Oct
- Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?8 Oct
- Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper8 Oct
Same family
Gemini 2 Pro- 8.7
- 15.0
Alternatives
other vendors · similar capability- 12.7
- 18.5
- 18.9
- 14.2
Using Gemini 2.5 Pro at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.







