gemini-2.5-pro-preview

completions

bygemini

gemini-2.5-pro-preview

completions

Published by: googleProvider:

gemini

Gemini 2.5 Pro Experimental is Google's state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.

Released

Jun 5, 2025

Knowledge

Jan 31, 2025

License

Proprietary

Context

Input

$1.25 / 1M tokens

Output

$10 / 1M tokens

Capabilities: tools

Accepts: text, image, audio, video

Returns: text

Released Jun 5, 2025Knowledge Cutoff: Jan 31, 2025License: Proprietary

Context: 1M Input: $1.25 / 1M tokensOutput: $10 / 1M tokensCapabilities: toolsAccepts: text, image, audio, videoReturns: text

Access gemini-2.5-pro-preview through LangDB AI Gateway

Recommended

Integrate with google's gemini-2.5-pro-preview and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for gemini-2.5-pro-preview

Category Performance Scores:

Science: Score 85.60 (Top 0% - Rank #0)
Vision: Score 82.00 (Top 4% - Rank #14)
Writing: Score 86.40 (Top 0% - Rank #0)

Overall Performance: 84.66666666666667 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
GPQA	86.40	Top 1%	STEM (Physics, Chemistry, Biology)
MMMU	82.00	Top 4%	General Knowledge

GPQA Score: 86.40 - Graduate-level reasoning benchmark

Model Comparison:

Provider: gemini

Model Type: completions

Context Size: 1000000 tokens

Comparing against 345 models in the database

Performance Analytics for gemini-2.5-pro-preview

Usage Statistics (Last 3 Days):

Total Requests: 62 API calls
Average TPS: 595.59 tokens per second
Average Response Time: 7564.20ms
Average Time to First Token: 5889.00ms
Total Cost: $0.60
Average Request Cost: $0.0097

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/14/2025	56	714.00	6780.80ms	5305.00ms	$0.50
9/16/2025	5	91.93	17828.80ms	13586.20ms	$0.10
9/17/2025	1	0.00	109.70ms	109.70ms	$0.00

Performance Summary:

Model: gemini-2.5-pro-preview by gemini

Monitoring Period: 9/13/2025 to 9/20/2025

Average Daily Requests: 21

Peak Daily Requests: 56

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

595.59 tokens/s

Category Scores

science#1 vision#2 writing#1

Benchmark Tests

View Other Benchmarks

GPQA

86.4

STEM (Physics, Chemistry, Biology)

MMMU

82.0

General Knowledge

Metric	GPQA	MMMU
Score	86.4	82.0

Compare with Similar Models

Code Examples

Integration samples and API usage

Code Samples for gemini-2.5-pro-preview

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="gemini-2.5-pro-preview",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "gemini-2.5-pro-preview",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro-preview",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gemini-2.5-pro-preview

Provider: gemini

API Endpoint: $https://api.us-east-1.langdb.ai