← All Models
Gemini 4 Argon
Google's flagship Gemini 4 Argon reasoning model for complex coding, research, and agentic work. Text, image, audio, video, and PDF input; text output. One 1,048,576-token window is shared by input, thinking, and output. Up to 65,536 output tokens per chat request (Chat Completions and Messages) and 32,768 per queued job or session turn, including thinking. Adjustable low, medium, or high thinking.
Web Search
Web Fetch
Code Execution
Specifications
| Provider | |
| Category | Text |
| Context window | 1.0M tokens |
Pricing (Starter tier)
260.00 credits / 1M input tokens
13.00 credits / 1M cached input tokens
1,300.00 credits / 1M output tokens
Introductory rates through November 30, 2026
Higher tiers get volume discounts. See tiers
Quick Start
curl -N https://query.genx.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-4-argon","messages":[{"role":"user","content":"Review this module."}],"reasoning_effort":"high","stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | Input text prompt |
system_prompt |
string | optional | — | System instructions |
max_tokens |
number | optional | 32768 |
1 to 32768 output tokens including thinking (non-streaming generateContent limit); use streaming chat for up to 65536 |
reasoning_effort |
string | optional | medium |
low, medium, or high; minimal is not supported |
tools |
array | optional | — | Built-in web_search, web_fetch, or code_execution |
Availability
Gemini 4 Argon is available in the GenX Pro App and via the GenX Router API.