Gemini 4 Argon is now available. Try it out.

What's new in Gemini 4 Argon

Gemini 4 Argon (gemini-4-argon) is our latest, most capable model. It can reason longer on hard problems for better results on complex coding, agentic, math, and science tasks. Gemini 4 Argon is available through the Gemini API and in Google AI Studio.

Gemini 4 Argon supports a unified 1M-token context window, long decode up to 1M tokens, and tunable thinking levels (low, medium, high).

Try it in AI Studio

Build apps from scratch with Gemini 4 Argon and AI Studio.

App Gallery

Play and remix apps, built with Gemini 4 Argon.

Get started

Get started with Gemini 4 Argon with starter prompts.

This guide explains what's new in Gemini 4 Argon, API changes, code examples, and migration guidance.

New model

Model	Model ID	Default thinking level	Pricing	Description
Gemini 4 Argon	`gemini-4-argon`	`medium`	Available through Nov 30, 2026 at an introductory price of $2/1M input tokens and $10/1M output tokens ($4/1M input and $20/1M output thereafter). See pricing for more details.	Our most capable model, built to solve the hardest problems with depth and precision across real-world software engineering and knowledge work tasks.

For complete details, see the Gemini 4 Argon model page. For introductory pricing details, see the pricing section later on this page or the pricing page.

Quickstart

Use the following example to send a request to gemini-4-argon with the recommended default thinking_level (medium) and a 64K output token limit:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-4-argon",
    input="Write a three.js script that renders a realistic 3D black hole with gravitational lensing."
)

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
  model: "gemini-4-argon",
  input: "Write a three.js script that renders a realistic 3D black hole with gravitational lensing.",
});

console.log(interaction.output_text);

REST

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "model": "gemini-4-argon",
    "input": "Write a three.js script that renders a realistic 3D black hole with gravitational lensing."
  }'

What's new in Gemini 4 Argon

Unified 1M input-output token limit: Input, thinking, and output share one window of 1,048,576 tokens.
Long decode: A single response can now go past 64K tokens, up to 1M tokens minus your input. See Long decode.
Agentic video understanding is generally available: Agentic video understanding is now generally available.
Supported in Managed Agents: The Antigravity agent in Gemini Managed Agents now supports Gemini 4 Argon.

For complete specs, see the Gemini 4 Argon model page. For pricing details, see the pricing page.

Larger output and long decode

Gemini 4 Argon can think longer on hard math, science, and coding problems.

Use thinking_level to control reasoning depth: The thinking level decides how deeply the model reasons before it answers. max_output_tokens is a hard limit: the response stops once thinking and output together reach it, so set it high enough that it doesn't cut the answer short.
Generate up to 1M tokens with background execution: Use background execution with max_output_tokens greater than 65,536 to let a single response go past 64K tokens, up to 1M tokens. The model generates long responses in hops of up to 64K tokens, and each hop continues from where the previous one stopped. With background execution, our servers run these continuation hops for you. Because each hop adds a model_output step to interaction.steps, join the text across all model_output steps when the interaction completes.

Python

import time
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-4-argon",
    input="Write a complete, rigorous proof of the prime number theorem.",
    background=True,
    generation_config={
        "max_output_tokens": 262144,
        "thinking_level": "high",
    },
)

while interaction.status in ("in_progress", "queued"):
    time.sleep(5)
    interaction = client.interactions.get(id=interaction.id)

# Each hop adds a model_output step, so join the text of all of them.
text = "".join(
    content.text
    for step in interaction.steps
    if step.type == "model_output"
    for content in step.content
    if content.type == "text"
)
print(text)
print("Status:", interaction.status)
print("Usage:", interaction.usage)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

let interaction = await client.interactions.create({
  model: "gemini-4-argon",
  input: "Write a complete, rigorous proof of the prime number theorem.",
  background: true,
  generation_config: {
    max_output_tokens: 262144,
    thinking_level: "high",
  },
});

while (interaction.status === "in_progress" || interaction.status === "queued") {
  await new Promise((resolve) => setTimeout(resolve, 5000));
  interaction = await client.interactions.get(interaction.id);
}

// Each hop adds a model_output step, so join the text of all of them.
const text = interaction.steps
  .filter((step) => step.type === "model_output")
  .flatMap((step) => step.content ?? [])
  .filter((content) => content.type === "text")
  .map((content) => content.text)
  .join("");
console.log(text);
console.log("Status:", interaction.status);
console.log("Usage:", interaction.usage);

REST

ID=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "input": "Write a complete, rigorous proof of the prime number theorem.",
    "background": true,
    "generation_config": {
      "max_output_tokens": 262144,
      "thinking_level": "high"
    }
  }' | jq -r '.id')

while true; do
  RESP=$(curl -s "https://generativelanguage.googleapis.com/v1beta/interactions/$ID" \
    -H "x-goog-api-key: $GEMINI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r '.status')
  if [[ "$STATUS" != "in_progress" && "$STATUS" != "queued" ]]; then
    echo "$RESP" | jq -r '[.steps[]? | select(.type == "model_output") | .content[]? | select(.type == "text") | .text] | join("")'
    break
  fi
  sleep 5
done

Background execution is the easiest way to run long decode. It runs the continuation loop server-side until the model finishes or reaches max_output_tokens. If you need finer-grained control over retries, backoff, and error handling (or don't want your interactions stored), you can use client-side continuation in the GenerateContent API. Client-side continuation is also coming soon to the Interactions API. For streaming, reconnection, token counting, and when to use long decode, see the long decode guide.

Setting output token limits

max_output_tokens sets the total thinking and output tokens for a response. Set it high enough that thinking doesn't cut the answer short, and low enough to limit spend when a hard prompt uses all of it.

Use these values as a starting point:

Standard tasks: Keep the default of 65,536 or don't set any value.
Existing apps with a limit lower than 32K: Raise max_output_tokens to at least 32,768. Gemini 4 Argon can spend more of the limit on thinking than earlier models. To use fewer tokens, lower the thinking level instead.
Complex reasoning and coding: Set background: true and set max_output_tokens to 131,072 or 262,144, up to 1,048,576 minus your input tokens.

Understanding thinking levels

The thinking level is your main control over quality, latency, and token use in Gemini 4 Argon:

Thinking level	Token use	When to use
`low`	Fewest tokens, lowest latency	Simpler tasks and cost-sensitive work. Also works for analysis and writing tasks that need light thinking. Quality can drop on hard tasks.
`medium` (default)	Balanced	Recommended for most tasks, including complex code and agentic use cases.
`high`	Most tokens, slowest first token	Complex reasoning, hard math and science, and the most difficult code or agent tasks. Pairs well with long decode for long outputs.

Run your evaluations at all three levels, then pick the lowest level that meets your quality bar. To learn more, see the thinking guide.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-4-argon",
    input="Analyze this payment processing pipeline for race conditions during retry attempts and rewrite the transaction locks safely.",
    generation_config={
        "thinking_level": "medium"  # Balanced reasoning effort for complex tasks
    }
)

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
  model: "gemini-4-argon",
  input: "Analyze this payment processing pipeline for race conditions during retry attempts and rewrite the transaction locks safely.",
  generation_config: {
    thinking_level: "medium", // Balanced reasoning effort for complex tasks
  },
});

console.log(interaction.output_text);

REST

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "model": "gemini-4-argon",
    "input": "Analyze this payment processing pipeline for race conditions during retry attempts and rewrite the transaction locks safely.",
    "generation_config": {
      "thinking_level": "medium"
    }
  }'

Gemini 4 Argon in Managed Agents

The Antigravity agent in Gemini Managed Agents supports Gemini 4 Argon. To use it, set the model in agent_config:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input=(
        "Audit https://web.dev for performance, Core Web Vitals, and SEO. "
        "Query Google's PageSpeed Insights API for both Mobile and Desktop strategies. "
        "Check search indexing with Google Search for site:web.dev. "
        "Format the output as a side-by-side scorecard table with prioritized fixes."
    ),
    environment="remote",
    agent_config={
        "type": "antigravity",
        "model": "gemini-4-argon",
    },
)

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
  agent: "antigravity-preview-09-2026",
  input:
    "Audit https://web.dev for performance, Core Web Vitals, and SEO. " +
    "Query Google's PageSpeed Insights API for both Mobile and Desktop strategies. " +
    "Check search indexing with Google Search for site:web.dev. " +
    "Format the output as a side-by-side scorecard table with prioritized fixes.",
  environment: "remote",
  agent_config: {
    type: "antigravity",
    model: "gemini-4-argon",
  },
}, { timeout: 300000 });

console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Audit https://web.dev for performance, Core Web Vitals, and SEO. Query Google'\''s PageSpeed Insights API for both Mobile and Desktop strategies. Check search indexing with Google Search for site:web.dev. Format the output as a side-by-side scorecard table with prioritized fixes.",
    "environment": "remote",
    "agent_config": {
      "type": "antigravity",
      "model": "gemini-4-argon"
    }
  }'

For more options, see model selection in the Antigravity agent guide.

Migration checklist

  `/gemini-api-dev migrate my app to Gemini 4 Argon`

Migrate to gemini-4-argon

Update model ID: Change your target model string to gemini-4-argon.
Review max_output_tokens: If you set it explicitly today, consider raising it. We recommend at least 32,768, since Gemini 4 Argon can spend more of the limit on thinking.
Configure thinking level: Choose low, medium (default), or high, and test your workload at all three.
Move off explicit context caching: Explicit caching (cachedContents / caches.create) is not supported on Gemini 4 Argon. Remove calls that create or reference cached_content from your requests. Implicit caching is enabled by default for prompts of at least 4,096 tokens and discounts cached input tokens by 95% on cache hits.
Remove sampling parameters: Remove temperature, top_p, and top_k from your requests. If provided, they are ignored.
Use background execution for long outputs: For tasks that need more than 64K tokens, set background to true and max_output_tokens greater than 65,536.
Increase client timeouts: Hard prompts can take several minutes. Use background execution, or set HTTP client timeouts to at least 15 minutes.
Keep conversation state on the server: Use previous_interaction_id for multi-turn and function calling conversations.

Pricing

Gemini 4 Argon is available at introductory pricing through November 30, 2026:

Input tokens: $2.00 per 1M tokens ($4.00 starting December 1, 2026)
- Cached input tokens: Implicit caching discounts cached input by 95%, to $0.10 per 1M tokens ($0.20 starting December 1, 2026).
Output tokens, including thinking tokens: $10.00 per 1M tokens ($20.00 starting December 1, 2026)

Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan. For complete pricing tiers, see the pricing page.

Other models

What's next

Read the long decode guide for streaming, reconnection, and token counting.
Learn how thinking levels and thought summaries work in the thinking guide.
Learn about long-running jobs in the background execution guide.
Test and refine prompts in Google AI Studio.