---
title: "Gemini 4 Argon — API access"
description: "Gemini 4 Argon API with low, medium and high reasoning, function calling, structured output and multimodal input. One key and balance with a flat 50% discount."
url: "https://apitoken.sale/models/gemini-4-argon"
language: "en"
---
# Gemini 4 Argon

Google’s frontier model for coding and complex work, with three reasoning levels, incremental streaming and a shared 1M-token context.

- **Model ID:** `gemini-4-argon`
- **Tier:** Argon
- **Context window:** 1M tokens shared by input, thinking and output
- **Max output:** 64K streaming · 32K non-streaming
- **Official price (per 1M):** $2 input / $10 output
- **Your price (per 1M):** input $1, output $5 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale` · **Endpoint:** `POST /v1beta/models/gemini-4-argon:generateContent` (x-goog-api-key)

## Best for

- Coding and complex analysis with low, medium or high reasoning.
- Function-calling agents and JSON schema output.
- Documents, images, audio and video in one shared context.

## Notes

- Use gemini-4-argon. Medium is the default; minimal and thinkingBudget are unsupported. Sampling controls are ignored.
- Text, inline image, WAV audio, MP4 video and PDF input; text output. Native Gemini, Chat Completions, Responses and Messages share one key and balance.
- Input, thinking and output share 1,048,576 tokens. This route supports up to 65,536 streaming or 32,768 non-streaming output tokens; long-decode continuation is unavailable.
- Implicit caching starts at 6,144 tokens and bills cached input at 5% of the input rate. Explicit caches, Batch and server-side tools are unavailable on this model.
- Official introductory rates end November 30, 2026. From December 1: $4 input, $0.20 cached input and $20 output per 1M tokens. The account discount applies after the active tariff.

## Call it

```bash
curl https://router.apitoken.sale/v1beta/models/gemini-4-argon:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**Which model ID do I use?**

Use gemini-4-argon on router.apitoken.sale. Select low, medium or high with thinkingLevel in Gemini requests or reasoning_effort in Chat Completions.

**Does the 1M context include output?**

Yes. Input, reasoning and response tokens share one 1,048,576-token window. The single-request output limit is 65,536 for streaming and 32,768 for non-streaming.

**What was verified?**

Incremental streaming, all three reasoning levels, JSON schema, function calls and tool results, implicit caching, image/audio/video/PDF input and long-context input. Batch, server-side tools and long-decode continuation are unavailable.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models