Gemini 4 Argon
Existing Gemini workflows. Efficient Gemini 4 reasoning and agentic workflows.
Which reasoning effort setting?
controls how long Gemini 4 Argon thinks before answering. Token prices never change; higher settings spend more and raise task cost.
Start at High. The top setting is also the best value here. Rule: cheapest setting within 2 points of the model’s best score.
At High, Argon thinks for about 68.3K tokens per task, then writes about 48.1K more as its answer: $9.95 per task, 1.2× Medium, for +2.8 points.
Output rate: $10.00/1M at every effort level. Thinking tokens are billed as output.
| Effort | Index | Per task | Thinking | All output | × Medium | Time |
|---|---|---|---|---|---|---|
| Medium | 47.6 | $8.63 | 55.1K | 100K | 1.00× | 28 min |
| HighStart here | 50.4 | $9.95 | 68.3K | 116K | 1.15× | 27.8 min |
Per task of the Artificial Analysis Intelligence Index: the average over its nine evaluations, counting input, cache, and output tokens at list prices. These are long, agent-style benchmark tasks, much longer than a chat message. Artificial Analysis prices this model at its 1 December rate ($4 / $20), so at today’s introductory price each task costs half.
Where Gemini 4 Argon sits on the frontier
Intelligence Index against one 100K-input, 10K-output request.