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 input-output token limit, long decode up to 1M tokens, and tunable thinking levels (low, medium, high).

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

New model

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:

pip install -U "google-genai>=2.30.1"

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-4-argon",
    contents="Write a three.js script that renders a realistic 3D black hole with gravitational lensing.",
    config=types.GenerateContentConfig(
        max_output_tokens=65536,
        thinking_config=types.ThinkingConfig(thinking_level="medium"),
    ),
)

print(response.text)

npm install "@google/genai@>=2.29.1"

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

const ai = new GoogleGenAI({});

const response = await ai.models.generateContent({
  model: "gemini-4-argon",
  contents: "Write a three.js script that renders a realistic 3D black hole with gravitational lensing.",
  config: {
    maxOutputTokens: 65536,
    thinkingConfig: {
      thinkingLevel: "medium",
    },
  },
});

console.log(response.text);

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-4-argon:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [{
      "parts": [{"text": "Write a three.js script that renders a realistic 3D black hole with gravitational lensing."}]
    }],
    "generationConfig": {
      "maxOutputTokens": 65536,
      "thinkingConfig": {
        "thinkingLevel": "medium"
      }
    }
  }'

What's new in Gemini 4 Argon

• Unified 1M input-output token limit: Input, thinking, and output tokens share a single 1M-token window, with a 32K per-request cap for non-streaming calls and a 64K per-stream cap for streaming calls.
• Long decode up to 1M tokens: The model can generate past the per-request cap, up to 1M tokens minus your input. The latest Google GenAI SDKs continue for you by default.
• Agentic video understanding (GA): Agentic video understanding is now generally available.
• Supported in Managed Agents: The Antigravity agent in Gemini Managed Agents now supports Gemini 4 Argon.

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

Larger output and long decode

When a task requires deep reasoning, Gemini 4 Argon can think longer and work harder to finish complex math, science, and coding problems in a single generation.

• Unified 1M input-output token limit: Argon can use up to 1M tokens, minus your input tokens, for thinking and output combined.
• Thinking tokens count toward max_output_tokens: On hard tasks, the model uses more of your max_output_tokens budget to reach a better answer. Use thinking_level to control token use.
• Per-request caps (64K streaming / 32K non-streaming): One streaming request returns up to 65,536 tokens. One non-streaming request returns up to 32,768 tokens, down from 65,536 on Gemini 3.x. For REST calls, these caps are also the defaults.

The latest Google GenAI SDKs run long decode for you by default. Use Python google-genai 2.30.1 or higher, or JavaScript @google/genai 2.29.1 or higher.

In these versions, automatic_continuation is True by default, so you do not need to set it. When you set max_output_tokens above the per-request cap, generate_content and generate_content_stream automatically continue across requests until the model finishes or reaches max_output_tokens, returning one combined response.

response = client.models.generate_content(
    model="gemini-4-argon",
    contents="Write a complete, rigorous proof of the prime number theorem.",
    config=types.GenerateContentConfig(
        max_output_tokens=262144,
        thinking_config=types.ThinkingConfig(thinking_level="high"),
        automatic_continuation=True,  # Default.
    ),
)

To run the loop yourself, set automatic_continuation=False. If you call REST or use an older SDK, requests stop at the per-request cap. For REST loops, third-party frameworks, 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 generation, including all continuation requests. Set it high enough that thinking does not cut the answer short. Set it low enough to limit spend when a hard prompt uses all of it.

Use the following guidance as a starting point:

• Standard tasks: Keep the default.
• Existing apps with a limit lower than 32K: Raise max_output_tokens to 32,768. To use fewer tokens, lower thinking_level.
• Tasks that used more than 32K tokens before: Set max_output_tokens to 65,536.
• Complex reasoning and coding: Set max_output_tokens to 131,072 or 262,144, up to 1,048,576 minus your input tokens.

If a request uses all of max_output_tokens, it returns finish_reason: "MAX_TOKENS" and includes a continuation_token. You can resume or start again.

• Resume from the checkpoint: Send the original request with the latest continuation_token and a higher max_output_tokens. If you do not raise max_output_tokens, the request returns 400 INVALID_ARGUMENT.
• Start again: Send the original request with a higher max_output_tokens and no continuation_token.

Understanding thinking levels

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

Run your evaluations at all three levels with a high max_output_tokens so the limit doesn't cut answers short. Then pick the lowest thinking_level that meets your quality bar.

Migration checklist

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

Migrate to gemini-4-argon

• Update the model ID: Change your model string to gemini-4-argon.
• Set max_output_tokens explicitly: The default is 64K for streaming and SDK calls, and 32K for non-streaming REST calls.
• Raise caps lower than 32K: Raise any cap lower than 32K to at least 32,768. Use thinking_level to reduce token spend.
• Plan for long decode: For tasks above the per-request cap, use the latest SDK or add a continuation_token loop.
• Replace thinking_budget with thinking_level: thinking_budget still works and maps to the nearest thinking_level, but it returns a warning. Test your workload at low, medium, and high.
• Move off explicit context caching: Explicit caching (cachedContents / caches.create) is not supported on Gemini 4 Argon and returns an error. Remove calls that create or pass cached_content in GenerateContentConfig. 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 deprecated parameters: Remove temperature, top_p, top_k, and candidate_count from requests. If provided, sampling parameters are ignored.
• Increase client timeouts: Set HTTP client timeouts to at least 20 minutes per call.
• Preserve thought signatures: Pass the full conversation history, including thought signatures, in multi-turn and function-calling requests.

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

• Gemini 3.8 Flash
• Gemini 3.6 Flash and 3.5 Flash-Lite
• See all models

What's next

• Read the long decode developer guide for full streaming, reconnection, and token-counting patterns.
• Learn how thinking levels and thought summaries work in the thinking guide.
• Test Gemini 4 Argon in Google AI Studio.