Google: Gemini 4 Argon
google/gemini-4-argon
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog entry, google/gemini-4-argon is a Google flagship reasoning model aimed at complex software engineering, mathematical and scientific problem solving, and autonomous multi-step agents. It accepts text, image, file, audio, and video inputs and returns text, with a listed context window of roughly one million tokens. Reasoning is mandatory, with selectable effort levels. The catalog reports Design Arena results that vary by category and an Artificial Analysis intelligence index, but no independent model card was available in this source pack.[1]
Strengths
- Catalog-listed multimodal input support (text, image, file, audio, video) with text output and a context window of about one million tokens.[1]
- Reasoning effort is configurable across low, medium, and high settings, and the catalog lists tool use, structured outputs, seed, and other tuning parameters.[1]
- Measured Design Arena entries in the catalog report higher win rates in 3D and game development categories than in spreadsheet tasks.[1]
Limitations
- All evidence here comes from a single OpenRouter catalog entry; no independent model card was available in this source pack, so capabilities and results should be validated on real workloads.[1]
- The catalog marks reasoning as mandatory, so it cannot be fully disabled, which may affect latency and cost on simple tasks.[1]
- Reported arena results were uneven across categories, with a notably low win rate on spreadsheet tasks, and the catalog lists no knowledge cutoff.[1]
Where to use it
- Worth evaluating for complex software engineering and autonomous multi-step agent workflows, which the catalog description names as its focus, alongside listed tool-use parameters.[1]
- Potential fit for mathematical and scientific problem solving where adjustable reasoning effort is useful.[1]
- Candidate for multimodal pipelines that ingest images, files, audio, or video and require text output, given the cataloged modalities.[1]
Sources
- [1] OpenRouter catalog · Google: Gemini 4 ArgonSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
Specifications
- Model ID
- google/gemini-4-argon
- Canonical ID
- google/gemini-4-argon-20261013
- Creator
- Added to OpenRouter
- 13.10.2026
- Context length
- 1,048,576
- Modality
- text+image+file+audio+video->text
- Input modalities
- audio, file, image, text, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $10
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | AA — next 20% of the cohort | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 50.4 | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · agenticgamedevwin rate 51.1% · rank 1 | 1,265Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · blender3dwin rate 65.7% · rank 1 | 1,378Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · pdfwin rate 69.2% · rank 4 | 1,298Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 33.9% · rank 11 | 1,203Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 49.8% · rank 11 | 1,356Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 53.5% · rank 11 | 1,327Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 60.5% · rank 10 | 1,326Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 53.5% · rank 8 | 1,362Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 62% · rank 1 | 1,336Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 58.4% · rank 11 | 1,336Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 55.5% · rank 7 | 1,317Elo | SS — top 10% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Google AI Studio | 1,048,576 | $1 | $5 | — | — | 100% |
| 1,048,576 | $2 | $10 | — | — | 100% | |
| Google AI Studio | 1,048,576 | $2 | $10 | — | — | 0% |
| 1,048,576 | $2.2 | $11 | — | — | 100% | |
| 1,048,576 | $3.6 | $18 | — | — | 100% | |
| Google AI Studio | 1,048,576 | $3.6 | $18 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
- Google introduces Gemini 4 Hydrogen, a fast model for everyday and agentic workflowsGoogle launches Gemini 4 Hydrogen, a speed-focused model for coding and agentic work, across the Gemini app, Search, AI Studio, the Gemini API, and enterprise surfaces, with flat pricing over a 1 million-token context.
- Google releases Gemini 4 Carbon, its strongest model for cybersecurity and agentic workGoogle has opened access to Gemini 4 Carbon through its API and Google AI Ultra subscriptions, citing leading benchmark results in agentic workflows, cybersecurity, and scientific reasoning.
- Google DeepMind and Artificial Analysis Introduce MKA, a Benchmark for Visually Grounded Agent WorkMKA is a 200-task benchmark that measures whether AI agents can extract decisive evidence from blueprints, scans, and charts and turn it into professional deliverables.