Gemini 2.5 Pro

google/gemini-2.5-pro
VisionAudioToolsJSONReasoning
by Google · 2025-06-17

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

ctx1.05M tokens
Max output65.5K
Inputtext + image + file + audio + video
Outputtext
p50 TTFT7.22 s
INPUT$2.50/ 1M tokens
OUTPUT$15.00/ 1M tokens
p50 TTFT7.22 s7d
p95 TTFT10.00 s7d
TRAFFIC1.5Mtokens / 7d

Google Gemini 2.5 Pro is a large language model developed by Google, designed for complex reasoning and multimodal understanding. It processes text, image, file, audio, and video inputs, and comes…

What is Google Gemini 2.5 Pro?

Who should use Gemini 2.5 Pro?

What are the key specifications of Gemini 2.5 Pro?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Gemini SDKhttps://api.orcarouter.ai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="google/gemini-2.5-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Pricing

Input / 1M tokens$2.50
Output / 1M tokens$15.00
Cache read / 1M$0.250
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $62.50 · With prompt caching $54.63

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.007550

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
7.22 s
Output speed
353 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

31.9
AA Coding
Better than 35% of models compared
#69 of 106
34.6
AA Intelligence
Better than 35% of models compared
#72 of 110
87.7
AA Math
Better than 75% of models compared
#20 of 81
AIME
88.7
AIME 2025
87.7
GPQA Diamond
84.4
Humanity's Last Exam
21.1
IFBench
48.7
LiveCodeBench
80.1
Long-Context Recall
66.0
MATH-500
96.7
MMLU-Pro
86.2
SciCode
42.8
TerminalBench Hard
26.5
τ²-Bench
54.1
Source: artificialanalysis.ai

How it compares

Gemini 2.5 ProGemini 3.1 Pro PreviewGemini 3.1 Pro Preview Custom ToolsGemini 3 Flash Preview
Input $/M$2.50$2.00$4.00$0.50
Output $/M$15.00$12.00$18.00$3.00
Context1.0M1.0M1.0M1.0M
Quality6/1010/1010/109/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost per token for Gemini 2.5 Pro through OrcaRouter?
Input tokens are $2.50 per 1M tokens, output tokens are $15.00 per 1M tokens. These are the provider rates with zero markup, billed exactly as shown.
How large is the context window?
The context window is 1,048,576 tokens (1M), and the maximum output is 65,536 tokens.
What are the main strengths of Gemini 2.5 Pro?
Strengths include a very large 1M token context, strong math reasoning (96.7 on MATH-500), and support for multimodal inputs: text, image, file, audio, and video.
How does Gemini 2.5 Pro compare to Gemini 1.5 Pro?
Gemini 2.5 Pro has improved reasoning, newer training, and adds audio/video input support. It is more expensive: input $2.50 vs $1.25, output $15 vs $5 per 1M tokens. Both have 1M context.
Does OrcaRouter process or store my data when using this model?
OrcaRouter acts as a gateway. Your data is sent to Google's API. OrcaRouter's data handling policies are not detailed here; refer to OrcaRouter's privacy policy. Google's policy applies for processing.
How can I call Gemini 2.5 Pro using an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1, use model ID "google/gemini-2.5-pro", and provide your OrcaRouter API key. Use standard chat completions format.
What input modalities does Gemini 2.5 Pro support?
It supports text, image, file (PDF, etc.), audio, and video as inputs.
Is there any markup or additional fee on top of the provider pricing?
No. OrcaRouter bills at the provider rate with zero markup. You pay exactly $2.50 per 1M input and $15.00 per 1M output tokens.

Embed this badge

Google: Gemini 2.5 Pro$2.50/M in7222ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/google/gemini-2.5-pro" target="_blank"> <img src="https://www.orcarouter.ai/embed/google/gemini-2.5-pro.svg" alt="Google: Gemini 2.5 Pro on OrcaRouter" /> </a>
Markdown [![Google: Gemini 2.5 Pro](https://www.orcarouter.ai/embed/google/gemini-2.5-pro.svg)](https://www.orcarouter.ai/models/google/gemini-2.5-pro)

Model card as data

GET /api/public/models/google/gemini-2.5-proOpen
Machine-readable:/llms.txt/llms-full.txt