Gemini 4 Argon Official Specifications, Pricing & Benchmarks
Google Gemini 4 Argon native omni-modal flagship with 1,048,576 context window.
📋 Gemini 4 Argon Official API & System Card Specifications
Verified against official Google DeepMind developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- gemini-4-argon
- Release Date
- 2026-10-13
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 1,049,000 tokens (1049K)
- Max Output Tokens
- 32,768 tokens
- Input Modalities
- Text + Image + Video + Audio + PDF
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 2
- Cached Input / 1M
- $ 0.1 -95%
- Output / 1M Tokens
- $ 10
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Gemini 4 Argon Full Benchmark Scorecard
18 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 6 items
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
CWE-Bench evaluates autonomous agents on finding and patching real-world software vulnerabilities.
Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences.
Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.
FrontierSWE V2 evaluates agents on open-ended technical projects and reports mean@5. Kept separate from FrontierSWE V1 dominance-score results, which are not comparable.
PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as…
🤖 Agents & Tools 7 items
LABBench2 evaluates models on real-world biology research tasks.
OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.
Vals Index measures economic impact across finance, coding, legal, and tax work, with every sector weighted by its contribution to U.S. GDP.
Vals Finance Agent v2 evaluates AI agents on realistic financial analyst tasks.
AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.
Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.
Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.
👁️ Multimodal 2 items
LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets.
Chartography visual chart recognition evaluated without tools, distinct from tool-assisted results.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Gemini 4 Argon
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Gemini 4 Argon open-source or proprietary?
Gemini 4 Argon (gemini-4-argon) is a proprietary commercial model by Google DeepMind. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Gemini 4 Argon?
Gemini 4 Argon supports 1049K input context and 32,768 max output tokens, priced at $2/1M input ($0.1/1M cached) and $10/1M output.