# Gemini 4 Argon API

Gemini 4 Argon is Google's flagship reasoning model for complex software engineering, math and science, and autonomous multi-step agents, with a 1,048,576-token context window shared between input and output; list price $2.00 in / $10.00 out per 1M tokens, provider list as at 1 November 2026.

- Provider: Google
- Model ID: gemini-4-argon
- Type: Chat
- Region: Global (provider global routing)
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Modalities: text, vision, audio, tools, reasoning
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 2.00 | 3.06 |
| Output | 10.00 | 15.30 |
| Cached input | 0.10 | 0.15 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=gemini-4-argon

The list price shown is Google's dated price through 30 November 2026; from 1 December 2026 Google lists $4.00 in / $20.00 out and $0.20 cached per 1M tokens. Global: runs on the provider's global routing; no Australian-region option as at 1 November 2026.

## Strengths

- Accepts text, image, video, audio and PDF input
- Thinking levels low, medium and high
- Up to 65,536 output tokens per synchronous request, or up to 1,048,576 with Google's long-decode mode
- Function calling and structured outputs

## Typical use cases

- Agentic software engineering across large codebases
- Math, science and quantitative analysis
- Multi-step agents that combine documents, images and audio
- Long-form generation such as reports and complete code files

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-4-argon","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

Global: Served on the provider's global routing.

## Related models

- [Gemini 3.8 Flash](https://seedrise.ai/models/gemini-3.8-flash): US$0.75 input · US$3.75 output per 1M tokens, Global
- [Gemini 3.5 Flash](https://seedrise.ai/models/gemini-3.5-flash): US$1.50 input · US$9.00 output per 1M tokens, AU
- [Gemini 3 Pro Image (Nano Banana Pro)](https://seedrise.ai/models/gemini-3-pro-image): US$0.13 per image · 1K / 2K, Global
- [Gemini 3.1 Flash Image (Nano Banana 2)](https://seedrise.ai/models/gemini-3.1-flash-image): US$0.067 per image · 1K, Global
- [Veo 3.1](https://seedrise.ai/models/veo-3.1): US$0.40 per second · 1080p, audio, US
- [Claude Sonnet 5.5](https://seedrise.ai/models/claude-sonnet-5-5): US$2.00 input · US$10.00 output per 1M tokens, AU
- [GPT-6.1 Sol](https://seedrise.ai/models/gpt-6.1-sol): US$2.00 input · US$10.00 output per 1M tokens, Global
- [Kimi K3.1 Pro](https://seedrise.ai/models/kimi-k3.1-pro): US$2.00 input · US$10.00 output per 1M tokens, Global

## FAQ

### What is the model ID for Gemini 4 Argon?

Use gemini-4-argon as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for Gemini 4 Argon compare to the list price?

Google's list price as at 1 November 2026 is US$2.00 per 1M input tokens and US$10.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.

### What is the context window and max output of Gemini 4 Argon?

Gemini 4 Argon has a context window of 1,048,576 tokens and a maximum output of 65,536 tokens, per the provider documentation checked on 1 November 2026.

### Can Gemini 4 Argon run in Australia?

Not at present. Gemini 4 Argon is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### What happens to Gemini 4 Argon pricing on 1 December 2026?

Google's list price moves from $2.00 in / $10.00 out to $4.00 in / $20.00 out per 1M tokens, and cached input from $0.10 to $0.20. Provider price changes reach your rate card only with written notice.

### Does Gemini 4 Argon support context caching?

Implicit caching only. Google applies the cached rate automatically when a request repeats an earlier prefix; explicit cache creation is not supported on this model.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/gemini-4-argon