GoogleMediumHigh

Gemini 4 Argon

Google's flagship reasoning model (GA 2026-10-13). A 1M-token context window with 65,536 max output tokens (thinking included), multimodal input, adjustable thinking levels and agentic tool use, priced at $4 input / $20 output per million tokens with implicitly cached inputs at $0.20/M.

7,432/37,160credits

input / output · per 1M tokens

Gemini 4 generation flagship reasoning model

1,048,576 token context window

65,536 max output tokens (thinking + output)

Multimodal input: text, image, audio, video, PDF

Thinking levels: low, medium (default), high

Function calling, structured outputs, search grounding, code execution, URL context

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Model Specifications

Context Window

1.0M

tokens

Max Output

66K

tokens

Training Cutoff

Not published

Compatible SDK

OpenAI, Google AI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	7,432	$4.95
Output Tokens	37,160	$24.77
Cached Tokens	371.6	$0.25

* 1,500 credits ≈ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Prove that there are infinitely many primes of the form 4k+3."
    }
  ],
  "max_tokens": 32768
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Array of message objects (OpenAI format). Supports text, image, audio, video, and PDF inputs.
`max_tokens`	integer	No	-	Maximum output tokens, thinking included — a hard limit. Max: 65,536. Context window (input + output): 1,048,576 tokens.
`response_format`	object	No	-	Output format constraint. Use `{ type: 'json_object' }` for structured JSON output.
`stream`	boolean	No	false	Enable Server-Sent Events streaming.

Examples

Hard Reasoning

A multi-step problem with room for thinking

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Prove that there are infinitely many primes of the form 4k+3."
    }
  ],
  "max_tokens": 32768
}'

Grounded Answer

Native Gemini API with Google Search grounding

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "contents": [
    {
      "parts": [
        {
          "text": "What changed in the latest stable Go release?"
        }
      ]
    }
  ],
  "tools": [
    {
      "google_search": {}
    }
  ]
}'

Tips & Best Practices

1Thinking tokens are billed at the output rate and count toward max_tokens — raise it (32,768+) for hard tasks, or lower the thinking level to spend less

2temperature, top_p and top_k are ignored by this model

3Implicit caching only (prompts of 4,096+ tokens, cached input $0.20/M); explicit cachedContents is not supported

4Google Search grounding is billed at 26.012 credits ($14/1k) per search query the model issues, on top of tokens

5Priority inference (serviceTier: priority) bills token charges at 1.8x; flex and batch discounts are not passed through and settle at the standard rate

6Long decode (background: true, over 65,536 output tokens) is not supported through the gateway