Models / Gemini 2.5 ProID: vertex_ai/google/gemini-2.5-pro
chat model by Google

Gemini 2.5 Pro

Gemini 2.5 Pro is Google's reasoning foundation model featuring adaptive thinking and a one million token context window, built for complex coding, STEM reasoning, and document analysis.

Certified & verified by nRouter· facts checked 2026-09-14 against 2 official sources

PlaygroundQuick Start
Context window1.05M
Max output66K
Maker

Google

Served On

Google Vertex AI

Specifications

Context window, ranked against other chat models

Proportional scale: 0 to 1.05M tokens. Not ranked, no published context window: glm-5.3-prime, qwen3-235b-a22b-2507, qwen3.7-max-2026-05-17, claude-opus-5-5.

Context window

1.0M

tokens
Max output

66K

tokens
Modality

chat

Vision
Function calling
System prompt

Benchmarks & Performance Rankings

Empirical intelligence benchmarks and category leaderboard placements for Gemini 2.5 Pro.

Compare in BenchmarksLeaderboard
Leaderboard Placements
#26
overallScore: 93.4%
#10
agentScore: 96.5%
#10
textScore: 96%
#14
webdevScore: 94.5%
#8
visionScore: 97.2%
#1
documentScore: 99.8%
#8
codingScore: 94.5%
#5
reasoningScore: 96.8%
#1
long contextScore: 99.9%
#1
multimodalScore: 99.5%
Core Benchmark DimensionsSource: Google DeepMind Technical Report & LMSYS
MMLUKnowledge

89.8%

HumanEvalCoding

93.1%

Latency p50TTFT

350ms

p99: 1120ms

ThroughputStream

95tok/s

SWE-bench: 48.6%

Recommended by nRouter Smart Routing: Enterprise codebase analysis and multimodal research. Key operational strength: 2M context window with frontier multimodal reasoning.

Benchmarks

LMSYS Chatbot Arena (text)Rank #77 · Score 1445
Source: arena.ai · Leaderboard: 2026-09-132026-09-14

Pricing

Rates are read live

Pricing for gemini-2.5-pro is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.

Provider-Reported Capabilities

What the hosting provider reports for this model, shown as it was returned. nRouter adds nothing to this report and infers nothing that is missing from it.

Version ID versionId

default

Launch Stage launchStage

GA

Supported Actions supportedActions
Open Generation AI Studio openGenerationAiStudio
References references
Us central1 us-central1

{}

Availability

Not enough data yet

We have not collected enough health probes for this model to publish an uptime or latency figure. A percentage from a handful of samples is fabricated precision, so none is shown until the sample count supports one.

How Gemini 2.5 Pro is billed

Billed at the provider's list price, with no per-token markup.

Exact list price
Tokens settle at the published rate of the model that served your call.
Cache discounts passed through
Provider prompt-caching discounts reach your balance with no added fee.
Cost on every response
Each response carries the x-nr-request-cost header, so you can reconcile spend per request.

More from Google

gemini-1.5-pro-002gemini-omni-1.1-flash-previewgemini-2.5-computer-use-preview-10-2025gemini-2.5-pro-exp-03-25

Start building with gemini-2.5-pro

One API key, three steps. Choose your tool to begin.

  1. Get a key

    Create API key

  2. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"

  3. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · vertex_ai/google/gemini-2.5-pro
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with vertex_ai/google/gemini-2.5-pro
claude --model vertex_ai/google/gemini-2.5-pro