GoogleOct 13, 2026
Gemini 4 Argon
Gemini 4 Argon is Google’s frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.
$2.50/$12.50
per 1M in / out
1M
context window
64K
max output
Time to first token—
Output speed—
Uptime—
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
InTextImageVideoAudio
OutText
Streaming
Function callingstream: truetoolsStructured outputsresponse_formatReasoningAlways onVisionUp to 1 imagesVideo inputVideo in messages
Audio inputAudio in messages
Web search
Prompt cachingReads at $0.125enable_web_searchNot supportedX search and log probabilities
Benchmarks
Specs
- Model ID
gemini-4-argon- Endpoint
POST /api/v1/chat/completions- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- Reasoning
- Always on
- Precision
- Set by the provider
- Privacy
- Anonymized
- Weights
- Closed
- Added
- Oct 13, 2026
Compare
| Model | Input | Output |
|---|---|---|
| Gemini 4 Argon | $2.50 | $12.50 |
| Kimi K3.1 Pro E2EE | $2.50 | $12.50 |
| Aion 3.5 | $3.75 | $7.50 |
| Aion 3.0 | $3.75 | $7.50 |
| Kimi K3.1 Pro | $2.00 | $10.00 |
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Input$2.50per 1M tokens
Cached input$0.12595% off input
Output$12.50per 1M tokens
Estimate a workload
$0.0112per request
$113for 10,000 requests
Blended price against similar models
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-argon",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'Base URL
https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | gemini-4-argon |
messages | text · image_url · video_url · input_audio |
max_completion_tokens | Up to 65,536 |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |