Gemini 4 Hydrogen is now available on OfoxView Google models on Ofox

Google: Gemini 4 Neon

Chat
google/gemini-4-neon

Gemini 4 Neon is Google’s model for fast, end-to-end completion of complex software engineering, knowledge work and science tasks. It accepts text, image, audio, video and PDF input and supports tool calling and structured output. Input, thinking and output share a 1,048,576-token window, with up to 65,536 output tokens per request by default. Thinking levels are low, medium, high and xhigh. Only implicit context caching is supported.

Context Window
1M
Max Output Tokens
66K
Released
2026-11-18
Capabilities
VisionFunction CallingReasoningPrompt CachingWeb SearchAudio InputVideo InputPDF Input
Available Providers
Gemini
Supported Protocols
openaigemini

Providers

Geminiprovider.type: "gemini"
Input Tokens
$3/M
Output Tokens
$15/M
Cache Read
$0.15/M
Audio Input
$3/M
Cached Image
$0.15/M
Cached Audio
$0.15/M
Cached Video
$0.15/M
Web Search
$0.014/R
Protocols
openai/v1/chat/completions
gemini

Documentation

How to call Gemini 4 Neon on OfoxAI: model IDs, request parameters and the errors you are most likely to hit.

Code Examples

from google import genai
client = genai.Client(
api_key="YOUR_OFOX_API_KEY",
http_options={"api_version": "v1beta", "base_url": "https://api.ofox.io/gemini"},
)
response = client.models.generate_content(
model="google/gemini-4-neon",
contents="Hello!",
)
print(response.text)

Frequently Asked Questions

Google: Gemini 4 Neon on Ofox.ai costs $3 per million input tokens and $15 per million output tokens. Pay-as-you-go, no monthly fees.