Hormouz AIHormouzSign in

Google: Gemini 2.5 Flash (batch): AI model

Context window:
1,048,576 tokens
Input:
$0.15/1M tokens
Output:
$1.25/1M tokens
Type:
text, image, audio, video
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Google: Gemini 2.5 Flash (batch) is a AI model from Google, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash:batch",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorGoogle
TypeText, Image, Audio, Video
Context window1,048,576 tokens
Pricing$0.15/M in · $1.25/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
79%
HLE
Humanity's Last Exam
12.1%
IFBench
Instruction-following
50.3%
AA-LCR
Long-context reasoning
65.3%
CritPt
Research-level physics reasoning
1.1%
AA Omniscience
Broad factual knowledge accuracy
26%
Non-Hallucination
Rate of avoiding fabricated answers
24.7%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
13.6%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
31.6%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 87%
1,031Elo
Win rate: 44.4%Avg time: 45.2s
Code
Top 82%
1,065Elo
Win rate: 45.4%Avg time: 74.6s
Data Viz
Top 83%
1,068Elo
Win rate: 46.8%Avg time: 57.6s
Game Dev
Top 86%
1,018Elo
Win rate: 43.6%Avg time: 78.2s
UI Component
Top 87%
1,012Elo
Win rate: 43.6%Avg time: 59.7s
Website
Top 80%
1,081Elo
Win rate: 45.6%Avg time: 78.0s
SVG
Top 90%
1,019Elo
Win rate: 43.1%Avg time: 17.5s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash:batch",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="google/gemini-2.5-flash:batch",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "google/gemini-2.5-flash:batch",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Google: Gemini 2.5 Flash (batch) API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Google: Gemini 2.5 Flash (batch) and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an accountBuy Gemini API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

Updated 2026-10-13