Google: Gemini 2.5 Flash

Fast Gemini workhorse for multimodal apps where latency and price matter

Model lab: Google
Model family: gemini-flash

Modalitiestext, image, audio, video, pdf → text

Context window1,048,576

Maximum output65,536

InputUSD 0.24 / 1M tokens

OutputUSD 2 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/google/gemini-2-5-flash.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/google/gemini-2-5-flash"

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 Flash API Pricing

Type	Price information
Input	USD 0.24 / 1M tokens
Output	USD 2 / 1M tokens
Cached input	USD 0.024 / 1M tokens

Benchmarks

Non-reasoning

Intelligence Index · v4.39.9

Coding Index—

Agentic Index—

Benchmark	Score	Measurement
Aider Polyglot	55.1	percent correct · Date: 2025-05-25
Artificial Analysis Coding Index	22.2	index · Date: 2026-06-02
SciCode	39.4	percent correct · Date: 2026-06-02
Terminal-Bench Hard	13.6	success rate · Date: 2026-06-02

Performance

Output speed203.48 tokens/s

Time to first token0.48 s

Time to first answer token—

End-to-end response time—

Measurement variant	Output speed	Time to first token	Time to first answer token	End-to-end response time
Non-reasoning	203.48 tokens/s	0.48 s	—	—

Performance trends

Throughput203.48 tok/sCurrent

Time to first token0.48 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current203.48 tok/s

Window average202.7 tok/s

Time to first token

Current0.48 s

Window average0.2 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current15.2 s

Window average16.2 s

Prompt cache hit rate

Current18.0%

Window average24.5%

Error rate

Current2.1%

Window average0.2%

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 Flash Compare models

Model	Input price	Output price	Context window	Capabilities
Gemini 2.5 FlashThis page	USD 0.24 / 1M tokens	USD 2 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 3.8 Flash	USD 0.6 / 1M tokens	USD 3 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 3.7 Flash	USD 0.6 / 1M tokens	USD 3 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini Flash Latest	USD 0.4 / 1M tokens	USD 2.4 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Gemini 3.6 Flash	USD 0.3 / 1M tokens	USD 1.5 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text, image, audio, video, pdf
Output: text
Context window: 1,048,576
Maximum output: 65,536
Release date: 2025-06-17
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Gemini 2.5 Flash for?

Fast Gemini workhorse for multimodal apps where latency and price matter

What inputs and outputs does Gemini 2.5 Flash support?

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

How is Gemini 2.5 Flash priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.24 / 1M tokens; Output USD 2 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Gemini 2.5 Flash?

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 moduck/google/gemini-2-5-flash. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

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.