Google
Gemini 2.5 Pro API
Gemini 2.5 Pro is Google DeepMind's flagship — strongest at long-context tasks thanks to its 1 million token window. Multimodal (text, image, video, audio), with strong reasoning and competitive pricing.
- Input
- $1.25
- Output
- $10.00
- Context
- 1M
- Vision
- Yes
/ 1M tokens
/ 1M tokens
tokens
Top use cases
- Long-document Q&A (entire codebases, books, transcripts)
- Video and audio understanding
- Multi-document research
- Long agentic conversations without context loss
Use Gemini 2.5 Pro in 30 seconds
ModelServer is OpenAI-compatible. Point your existing OpenAI SDK at modelserver.dev/v1 and set the model name to gemini-2.5-pro.
gemini-2-5-pro.py
from openai import OpenAI
client = OpenAI(
api_key="sk-modelserver-...",
base_url="https://modelserver.dev/v1",
)
response = client.chat.completions.create(
model="gemini-2.5-pro",
messages=[
{"role": "user", "content": "Hello, Gemini 2.5 Pro!"}
],
)
print(response.choices[0].message.content)Frequently asked questions
- How much does Gemini 2.5 Pro cost?
- Gemini 2.5 Pro is priced at $1.25 per 1M input tokens and $10.00 per 1M output tokens via ModelServer. ModelServer adds a flat 5.5% platform fee on top — no markups on individual tokens, no monthly minimum.
- What is the Gemini 2.5 Pro context window?
- Gemini 2.5 Pro supports a 1M token context window. You can put roughly 750,000 words in a single prompt.
- Is Gemini 2.5 Pro OpenAI-compatible via ModelServer?
- Yes. Point your OpenAI SDK base_url to https://modelserver.dev/v1 and set model="gemini-2.5-pro". Existing OpenAI-SDK code works without modification.
- Who is Gemini 2.5 Pro best for?
- Anything that needs to fit > 200K tokens in a single call.
- Does Gemini 2.5 Pro support vision input?
- Yes. Gemini 2.5 Pro accepts image inputs alongside text. Pass images as base64 or URL in the OpenAI-compatible message format.