Gemini 2.5 Flash

by Google · 1M context · fast

Ultra-fast and ultra-cheap. Best model for high-volume inference with 1M context. Ideal for RAG pipelines, classification, and data processing.

Use Gemini 2.5 Flash →

Pricing Comparison

Per 1 million tokens

	Official (Google)	NeatAPI	You Save
Input Tokens	$0.07	$0.07	$0.00
Output Tokens	$0.30	$0.28	$0.02

That's 5% savings on every API call. See full pricing →

Code Examples

Drop-in replacement — just change the base URL and API key.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.neatapi.ai/v1",
    api_key="your-neatapi-key"
)

response = client.chat.completions.create(
    model="gemini-2-5-flash",
    messages=[
        {"role": "user", "content": "Hello, world!"}
    ]
)
print(response.choices[0].message.content)

Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.neatapi.ai/v1',
  apiKey: 'your-neatapi-key'
});

const response = await client.chat.completions.create({
  model: 'gemini-2-5-flash',
  messages: [
    { role: 'user', content: 'Hello, world!' }
  ]
});
console.log(response.choices[0].message.content);

cURL

curl https://api.neatapi.ai/v1/chat/completions \
  -H "Authorization: Bearer your-neatapi-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2-5-flash",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ]
  }'