Gemini 4 Neon
Google logo

Gemini 4 Neon

gemini-4-neonllms.txt
Google
New
Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level intelligence and can rapidly handle complex software engineering, knowledge work, and scientific research tasks. It has a unified 1-million-token context window, with a maximum single-generation length of up to 1 million tokens.

Pricing

PricingCache ReadInput VideoInput AudioWeb Search
$3$15
$0.15/M tokens$3/M tokens$3/M tokens$0.014/request

Input Modalities

  • Text
  • Vision
  • Audio
  • Video
  • PDF

Output Modalities

  • Text

Context length

  • 1.05M tokens

Max output

  • 65.5K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

VertexAI gemini-4-neon
Pricing$3$15
Cache Read$0.15/M tokens
Input Video$3/M tokens
Input Audio$3/M tokens
Web Search$0.014/request
PrecisionⓘNot Disclosed
Latency12.9S
Throughput52.0TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
100.00% uptime today
Google AI Studio gemini-4-neon
Pricing$3$15
Cache Read$0.15/M tokens
Input Video$3/M tokens
Input Audio$3/M tokens
Web Search$0.014/request
PrecisionⓘNot Disclosed
Latency4.4S
Throughput874.3TPS
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
99.83% uptime today

Performance for gemini-4-neon

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gemini-4-neon",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is Gemini 4 Neon?

Gemini 4 Neon is the latest model in Google’s Gemini 4 series. It features frontier-level intelligence and can rapidly handle complex software engineering, knowledge work, and scientific research tasks. It has a unified 1-million-token context window, with a maximum single-generation length of up to 1 million tokens.