Gemini 4 Argon
Gemini 4 Argon is Google’s multimodal reasoning model, supporting text, image, and file inputs with configurable reasoning levels. It combines tool calling, structured outputs, and Google Search and Maps grounding to support document analysis and agent workflows. Long-form generation supports continuation across requests, allowing applications to resume output beyond a single request’s token limit.
- Language
- Reasoning
- File input
- Vision
- Tool use
- Web search
- Implicit caching
- Video input
- Structured output
- Context
- 1M
- Max output
- 1M
- Input / 1M
- $2.00
- Output / 1M
- $10.00
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass google/gemini-4-argon as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-4-argon",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$2.00
Output
Per 1M completion tokens
$10.00
Cache read
Per 1M cached prompt tokens
$0.100
A 1M-token prompt with 250K tokens of output costs about $4.50.