# Gemini 4 Argon (slim)

> Gemini 4 Argon is Google's efficient Gemini 4 reasoning model, spending fewer thinking tokens per turn than Carbon on coding, agentic, maths and science work, on the paid tier of the Gemini API with a 1,048,576-token shared limit.

- Full: https://www.anchorterminal.com/tools/gemini-4-argon.md (~9,700 tokens) · this version ~1,780 tokens · JSON https://www.anchorterminal.com/tools/gemini-4-argon.json · canonical https://www.anchorterminal.com/tools/gemini-4-argon
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-19 · pricing https://www.anchorterminal.com/tools/gemini-4-argon#pricing · reviews https://www.anchorterminal.com/tools/gemini-4-argon#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 65.3/100 · rank #545 of 1559 · #23 in Model APIs & inference · not agent-ready · confidence medium** · same model listed separately: Gemini Developer API, Model API (https://www.anchorterminal.com/tools/gemini-api.min.md)


Assessment: Google's efficient Gemini 4 reasoning model, generally available since 13 October, with a 1M-token shared budget, three thinking levels, function calling and structured output, and support on Cloud until October 2027 at the earliest. Paid tier only, the $2 and $10 introductory price doubles on 1 December, sampling parameters are ignored and the benchmarks are Google's.

## Facts

- Kind: Model API · vendor: Google · category: Model APIs & inference · legal entity: Google LLC · provenance 91/100
- Endpoint: `https://generativelanguage.googleapis.com/v1beta` ()
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed model, used through the Gemini API and Google's apps under Google's terms
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-19 01:38 UTC · uptime 30 days 100.0% (12 probes) · p50 42 ms · p95 245 ms over 24 hours
- Vendor status page: not read, no machine-readable status found (2026-11-19 01:01 UTC)
- Surface graded: The model as the Gemini API serves it, read on 18 November from Google's model page, the What's new in Gemini 4 Argon guide, the pricing page and release notes in AI Studio's docs, the DeepMind model card and the Google Cloud model page. Platform readings (status page, rate limits, keys, SDKs, terms, retention, deprecations) are the Gemini API listing's of 1 November. No account was made and nothing was called
- Model IDs: gemini-4-argon, stable, on the GenerateContent API and the Interactions API (not the Live API). On Google Cloud, gemini-4-argon-cyber-permissive, a version for defensive security work, is generally available behind an allowlist
- Context: 1,048,576 tokens for input, thinking and output together. 65,536 output tokens a synchronous response; background execution runs to the full budget in 64K hops. Knowledge cutoff March 2026
- Thinking: low, medium (the default) and high
- Inputs and outputs: Text, images, video, audio and PDF in; text, function calls and JSON to a schema out. Tools: Google Search and Maps grounding, code execution, URL context, computer use, file search and function calling. Agentic video understanding generally available. Batch, Flex and Priority inference supported
- Caching: Implicit caching only, on prompts of 4,096 tokens or more, with cached input 95% off: $0.10 per million to 30 November, $0.20 from 1 December
- Pricing: Introductory $2 input and $10 output per million tokens to 30 November 2026, then $4 and $20 from 1 December, thinking included. Paid tier only. Search grounding billed per query after 5,000 free requests a month shared across Gemini 3 and newer models
- Where: Gemini API paid tier and Google AI Studio; the Gemini app; Gemini for business; Google Antigravity; AI Mode in Google Search; Google Cloud's Agent Platform; the Antigravity agent in Gemini Managed Agents
- Retirement: Google Cloud lists 13 October 2027 or later for retirement of support on its Agent Platform, and says models may stay on the Gemini API after that. The Gemini API's deprecations give no date for Argon
- Google's figures: Vendor-reported, from the model card against GPT-6 Astra, Claude Fable 5.1 and Claude Opus 5.5: Vals Index 68.9% (63.1%, 65.8%, 67.0%), DeepSWE v1.1 77.9%, Terminal-bench 4.0 57.4% (Opus 66.4%), GraphWalks 256k to 1M 84.2%, LVBench 91.7%
- Safety: A new sparse mixture-of-experts model, not a fine-tune of an earlier one. The published safety report says the biological and cyber critical levels and the stealth and situational awareness alert level can't be ruled out, with safety cases and safeguards Google assesses bring the risk below them
- Prices: Gemini 4 Argon input $2 per 1M tokens; Gemini 4 Argon cached input $0.10 per 1M tokens; Gemini 4 Argon output $10 per 1M tokens

- Scores: Reliability 45, Performance not tested, Schema & documentation 85, Agent ergonomics 93, Security & auth 55, Payments & pricing 30, Task success not tested, Maintenance & community 87, Transparency & trust 73
- Why: Reliability, Model reading for gemini-4-argon on the Gemini API. · Schema & documentation, Model reading for gemini-4-argon on the Gemini API. · Agent ergonomics, Model reading for gemini-4-argon on the Gemini API. · Security & auth, Model reading for gemini-4-argon on the Gemini API. · Payments & pricing, Model reading for gemini-4-argon on the Gemini API. · Maintenance & community, Model reading for gemini-4-argon on the Gemini API. · Transparency & trust, Model reading for gemini-4-argon on the Gemini API.
- Sources: 11, open questions: 4, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/gemini-4-argon.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.

## Before you call it

1. Call generateContent at https://generativelanguage.googleapis.com/v1beta, or the Interactions API, with model gemini-4-argon and an x-goog-api-key on a billed project
2. Keep thinking_level at medium, the default, and raise it to high for hard maths, science and code
3. Set max_output_tokens to at least 32,768, since Argon spends more of the limit on thinking
4. Don't send temperature, top_p or top_k, and remove any cached_content fields
5. Budget for $4 input and $20 output per million tokens from 1 December 2026, or compare Neon at $3 and $15

## Connect

```bash
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-4-argon:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "content-type: application/json" \
  -d '{"contents":[{"parts":[{"text":"hello"}]}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Vertex AI (Gemini Enterprise Agent Platform) | AA | 91.2 | inference.llm | https://www.anchorterminal.com/tools/vertex-ai.min.md |
| OpenAI API | AA | 85.8 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| GPT-6.2 Astra | AA | 85.8 | inference.llm | https://www.anchorterminal.com/tools/gpt-6-2-astra.min.md |
| Amazon Bedrock | A | 83.5 | inference.llm | https://www.anchorterminal.com/tools/amazon-bedrock.min.md |
| Azure OpenAI in Foundry Models | A | 81.2 | inference.llm | https://www.anchorterminal.com/tools/azure-openai.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)

