Gemini 4 Neon API

Send text, images, audio, video or files to a reasoning model and get text back for coding and agents

Modalities
Audio, Image, Text, VideoText
In / Out price
$3/$15per 1M
Context window
1.05M tokens
Released
Nov 18, 2026

Gemini 4 Neon overview

The pelican test: one prompt, every text model, unedited SVG output from Nov 18, 2026.

SVG of a pelican riding a bicycle, written by Gemini 4 Neon through AI/ML API

Gemini 4 Neon by Google

Gemini 4 Neon is a Gemini 4 model from Google for coding, agentic and orchestration workflows. It supports reasoning, tools and structured output.

Gemini 4 Neon specs

Model ID
google/gemini-4-neon
Developer
Google
Context window
1,048,576 tokens
Max output
65,536 tokens
Input
Audio, Image, Text, Video
Output
Text
API
OpenAI-compatible, base URL https://api.aimlapi.com/v1

Built for tool-driven loops

Neon can request several tool calls in one turn through parallel tool calls. An orchestration step can fan out to independent tools and collect the results in a single round trip.

Streaming lets you show partial output while a long answer is generated. A reply can run up to 65,536 tokens, and the context window holds 1M tokens, so large codebases, long transcripts and video input fit in one request.

Set reasoning effort per task

Reasoning effort accepts low, medium or high. Lowering it can give faster responses and use fewer tokens on reasoning. Raising it gives the model more room to work through a hard problem.

Start with medium on your real prompts. Move routine steps such as formatting or simple lookups to low, then compare high on the tasks where medium gives wrong or shallow answers.

Neon, Hydrogen, Carbon or Argon

Google positions Gemini 4 Hydrogen as a fast, efficient model for everyday coding and agentic workflows. Gemini 4 Carbon is described as a frontier model for coding, agentic and complex reasoning work. Gemini 4 Argon is Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.

Run the same agent task on Neon and on the neighbouring model that matches your difficulty level, then check which one completes the tool calls correctly.

Use cases

Generate and refactor code across a large repository loaded into the 1M-token context.

Run an orchestrating agent that dispatches parallel tool calls and merges their results.

Extract structured data from PDFs, screenshots, audio recordings or video clips.

Stream coding assistance into an editor or chat interface while reasoning effort stays low.

Capabilities

  • File input
  • Reasoning
  • Streaming
  • Structured outputs
  • Function calling
  • Vision

Gemini 4 Neon API pricing

Gemini 4 Neon pricing in US dollars
UsagePriceUnit
Input$31M tokens
Output$151M tokens
Cached input$0.151M tokens

Prices from the AI/ML API price list, checked on Nov 18, 2026.

Gemini 4 Neon vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
ModelInputOutput
Gemini 4 Neon$3$15
Gemini 3.8 Flash$0.75$3.75
Gemini 3.7 Flash$0.75$3.75
Gemini 3.6 Flash$1.5$7.5
Gemini 4 Argon$2$10

How to use the Gemini 4 Neon API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-4-neon",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

Related articles

All posts

Gemini 4 Neon FAQ

How much does Gemini 4 Neon cost?

Gemini 4 Neon costs $3 / 1M tokens for input and $15 / 1M tokens for output on AI/ML API. Cached input is billed at $0.15 / 1M tokens.

What inputs does Gemini 4 Neon accept?

It accepts text, images, audio, video and files. The output is text.

Which request option controls reasoning?

Reasoning effort accepts low, medium or high. Lower values can speed up responses and reduce tokens spent on reasoning.

What is the Gemini 4 Neon model ID?

Use google/gemini-4-neon as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of Gemini 4 Neon?

Gemini 4 Neon accepts up to 1,048,576 tokens of context and returns up to 65,536 output tokens.

Start building with Gemini 4 Neon

Gemini 4 Neon API

google/gemini-4-neon

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-4-neon",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'