Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google Gemini 4 Flagship Reasoning, with a 1M token context window.

POST/v1/ai/chat

$0.01/call

Overview

Property	Value
Model ID	`google/gemini-4-argon`
Context Window	1,048,576 tokens
Max Output	943,718 tokens
Input Price	$2.95 / 1M tokens
Output Price	$14.77 / 1M tokens

Usage

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'google/gemini-4-argon',
    messages: [{ role: 'user', content: "Explain why this recursive function overflows the stack for large inputs and rewrite it iteratively." }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "google/gemini-4-argon", "messages": [{"role": "user", "content": "Explain why this recursive function overflows the stack for large inputs and rewrite it iteratively."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `google/gemini-4-argon`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stream`	`boolean`	No	Enable SSE streaming	`false`

Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "google/gemini-4-argon",
    "message": {
      "role": "assistant",
      "content": "Each call adds a frame and the recursion depth grows with n, so inputs in the hundreds of thousands exceed the default stack. The iterative version keeps an explicit stack of pending nodes and loops until it is empty, using heap memory instead of call frames."
    },
    "usage": {
      "promptTokens": 24,
      "completionTokens": 180,
      "totalTokens": 204
    }
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"Each"},"model":"google/gemini-4-argon","index":0}
data: [DONE]

Under the Hood

We handle auth, billing, and response normalization — you just send messages.