Models
Gemini 4 Argon
Model id: gemini/models/gemini-4-argon
- Agentic
- Frontier
- Coding
- Reasoning
- Vision
- Multimodal
- Audio
- Video
- Long context
- Tools
Google’s most capable Gemini for hard coding, science, and agents that work through many steps.
Best for
hard coding, science, and long agent runs.
- Provider
- Google Gemini
- Context window
- 1,048,576
- Release date
- 2026-10-13
- Reasoning effort
- lowmediumhighDefault: medium
Pricing
Input
307.846 ¢ CA / 1M
Cached input
15.3923 ¢ CA / 1M
Output
1,539.23 ¢ CA / 1M
Web search
Per successful search
2.1549 ¢ CA / search
Billed on top of tokens when the model uses web search.
Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-10-23).
Performance
Reading
Last 7 days
Not enough data to display the chart.
Activity
Tokens
—
—
—
—
—
Top 5 tools · last 7 days
Not enough data to display tool activity.
Availability
Availability (%)
Last 7 days
- Operational probes
- 100% over 7 days
- Samples
- 9,115
Quick start
Call the API with a tonia_ key and the exact model id below.
curl
curl https://pass.tonia.ca:8443/v1/interactions \
-H "Authorization: Bearer $TONIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini/models/gemini-4-argon",
"input": [
{
"type": "text",
"text": "Bonjour"
}
],
"stream": false
}'Python (tonia SDK)
import os
from tonia import Tonia
client = Tonia(api_key=os.environ["TONIA_API_KEY"])
response = client.interactions.create(
model="gemini/models/gemini-4-argon",
input=[{"type": "text", "text": "Bonjour"}],
stream=False,
)TypeScript (tonia SDK)
import { Tonia } from "@tonia-router/sdk";
const client = new Tonia({
apiKey: process.env.TONIA_API_KEY,
});
const response = await client.interactions.create({
model: "gemini/models/gemini-4-argon",
input: [{ type: "text", text: "Bonjour" }],
stream: false,
});In Cursor, Cline, and other OpenAI-compatible tools, Gemini models use the gemini/models/ prefix (for example gemini/models/gemini-4-argon).