Google: Gemini 2.5 Pro Preview 06-05

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Model lab: Google
Model family: gemini

Modalitiespdf, image, text, audio → text

Context window1,048,576

Maximum output65,536

InputUSD 1 / 1M tokens

OutputUSD 8 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to google/gemini-2.5-pro-preview.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "google/gemini-2.5-pro-preview"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Gemini 2.5 Pro Preview 06-05 API Pricing

Type	Price information
Input	USD 1 / 1M tokens
Output	USD 8 / 1M tokens
Reasoning	USD 8 / 1M tokens
Cached input	USD 0.1 / 1M tokens
Cache write	USD 0.3 / 1M tokens

Performance

Performance trends

Throughput92.6 tok/sCurrent

Time to first token1.3 sCurrent

End-to-end latency8.0 sCurrent

Throughput

Current92.6 tok/s

Window average89.6 tok/s

Time to first token

Current1.3 s

Window average1.4 s

End-to-end latency

Current8.0 s

Window average7.5 s

Tail latency (P99)

Current29.9 s

Window average17.4 s

Prompt cache hit rate

Current26.2%

Window average24.0%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Gemini 2.5 Pro Preview 06-05 Compare models

Model	Input price	Output price	Context window	Capabilities
Gemini 2.5 Pro Preview 06-05This page	USD 1 / 1M tokens	USD 8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 4 Argon	USD 1.6 / 1M tokens	USD 8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 3.5 Transcribe Live	USD 0.00012 / second · Billed by input audio duration	Not billed on output	—	Text output
Gemini Embedding 2	USD 0.16 / 1M tokens	Not billed on output	8,192	Text output
Gemini Robotics-ER 1.6 Preview	USD 0.8 / 1M tokens	USD 4 / 1M tokens	131,072	Text output · Reasoning · Tool calling

Model specifications

Input: pdf, image, text, audio
Output: text
Context window: 1,048,576
Maximum output: 65,536
Release date: 2025-06-05
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Gemini 2.5 Pro Preview 06-05 for?

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

What inputs and outputs does Gemini 2.5 Pro Preview 06-05 support?

Recorded inputs: PDF, images, text, audio; outputs: text.

How is Gemini 2.5 Pro Preview 06-05 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 1 / 1M tokens; Output USD 8 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Gemini 2.5 Pro Preview 06-05?

Current model records list Context window 1,048,576 tokens; Maximum output 65,536 tokens.

What model parameter does the Quickstart use?

The example uses google/gemini-2.5-pro-preview. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.