Gemini 4 Argon
Google's flagship Gemini 4 model with a unified 1M-token context window and up to 1M-token output, built for long-horizon software engineering, enterprise knowledge work, and cyber defense.
Gemini 4 Argon is Google's flagship frontier model, released on September 30, 2026 as the first public model in the Gemini 4 family. Google positions it for long-horizon, multi-step work that runs for hours rather than seconds, naming real-world software engineering, enterprise knowledge work in legal and finance, and cybersecurity defense as its primary targets.
It runs on a unified 1M-token context window that spans both input and output. A single request defaults to 65,536 output tokens, and long decoding can extend that to 1M tokens, so the model can carry state across a large code migration or a full document set without stopping to re-prompt. Inputs cover text, images, video, audio and PDF with text output, and thinking level is selectable across LOW, MEDIUM and HIGH (MEDIUM by default). Function calling, structured outputs, code execution, file search, search grounding and URL context are supported, and implicit caching applies automatically to shared prompt prefixes of 6,144 tokens or more; explicit context caching, image and audio generation, and the Live API are not available.
Typical workloads include multi-file codebase migration and bug fixing, pulling detail out of charts and long video, multi-step finance and legal research, and defensive security work such as finding and patching vulnerabilities.
Updated:
MODEL ID
gemini-4-argon- Context
- 1.049M
- Max output
- 943.718K
- Recommended API
- messages
- Input
- audio / file / image / text / video
- Output
- text
Providers
5 providersCompare API prices across providers. Select a provider to view all charges and conditions.
Reasoning
- Default effort
- medium
- Always enabled
- Yes
- Available effort levels
- high / medium / low
Quick Start
Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.
Get your API key
Create a key from your Felo API Platform account and set it as an environment variable.
export FELO_API_KEY="YOUR_API_KEY"Make your first request
Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.
gemini-4-argonThis model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.
const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.FELO_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "gemini-4-argon",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());Using third-party SDKs
Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.
Enable streaming
Add stream: true to receive responses as server-sent events.
curl -N https://openapi.felo.ai/api/v1/messages \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-argon",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"stream": true
}'Endpoint
Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.
Messages
Anthropic-compatible messages for Claude-style clients.
POST
https://openapi.felo.ai/api/v1/messagesParameters
modelstringgemini-4-argonPublic model ID to call.max_tokensinteger—Maximum generated tokens.messagesarray—Conversation messages for Chat Completions.include_reasoning———reasoning———reasoning_effort———response_formatobject—Request structured output when supported.seed———stop———structured_outputs———temperaturenumber—Controls response variety when supported.tool_choicestring or object—Controls whether a tool should be called.toolsarray—Tool calling definitions following compatible schema.top_p———Frequently asked questions
What is Gemini 4 Argon?
Gemini 4 Argon is Google's flagship frontier model, released on September 30, 2026 as the first public model in the Gemini 4 family. Google positions it for long-horizon, multi-step work that runs for hours rather than seconds, naming real-world software engineering, enterprise knowledge work in legal and finance, and cybersecurity defense as its primary targets. It runs on a unified 1M-token context window that spans both input and output. A single request defaults to 65,536 output tokens, and long decoding can extend that to 1M tokens, so the model can carry state across a large code migration or a full document set without stopping to re-prompt. Inputs cover text, images, video, audio and PDF with text output, and thinking level is selectable across LOW, MEDIUM and HIGH (MEDIUM by default). Function calling, structured outputs, code execution, file search, search grounding and URL context are supported, and implicit caching applies automatically to shared prompt prefixes of 6,144 tokens or more; explicit context caching, image and audio generation, and the Live API are not available. Typical workloads include multi-file codebase migration and bug fixing, pulling detail out of charts and long video, multi-step finance and legal research, and defensive security work such as finding and patching vulnerabilities.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
