Turn these release notes into a step-by-step migration guide for developers, with code before/after examples and a checklist at the end. <paste notes here>
Gemini 4 Argon API
Google Gemini 4 Argon: multimodal reasoning model with a 1M-token context.
from$0.72/ 1M input tokens$0.810% off
Model IDgemini-4-argon
Input
Text
Output
Chat
Provider
7 providers
Last 7 days · not enough recent requests for stats yet.
Gemini 4 Argon pricing
Prices are per unit; requests without a provider are routed to the cheapest provider that supports your parameters.
| Option | Price (USD) |
|---|---|
| All options | $0.72 / 1M input tokens 72 Credits |
Try Gemini 4 Argon before you integrate
Test output quality, compare provider prices and estimate cost before writing any code.
Settings
Credits for max_tokens are held first, then settled to the actual usage.
Start a conversation. Replies stream in and are billed by actual token usage.
Gemini 4 Argon prompt examples
Ready-to-use prompts. Load one into the playground and tweak it.
21 prompts
Contract review
AnalysisRead this supplier contract and list every clause about liability, termination and auto-renewal, with a plain-language explanation of each. <paste contract here>
Browser game prototype
Creative codingCreate a single-file HTML5 canvas game where the player steers a paper plane through floating islands, with score and restart.
Please describe the content of this image/video/audio
what is difference between http and https
API examplewhat is difference between http and https
Summarize the content without using lists, Markdown, or exceeding 80 words
Instruction FollowingSummarize the content without using lists, Markdown, or exceeding 80 words.
Gemini 4 Argon API reference
Endpoints, request fields and runnable examples for this model.
Base URL
https://01router.com/api/v1Quick start
Set API_KEY to your project key, then run a sample from your server. Replace example media URLs with your own public URLs.
Auto-routing chooses a provider that supports the request. Select a provider to see its input constraints and pinned request examples.
curl https://01router.com/api/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-argon",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": false
}'Endpoints
Only endpoints relevant to this model are listed. Paths below include /api/v1. Click an endpoint to read its usage.
Authentication
Send your API key as a Bearer token. Requests are billed to the key owner's credits.
Authorization: Bearer YOUR_API_KEY
Content-Type: application/jsonInput
Send messages directly in the request body. Chat requests do not use an input wrapper.
Request body
| Name | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | "gemini-4-argon" |
| provider | string | No | Pin a provider; omit to auto-route to the cheapest. One of: wavespeed | kie | apimart | evolink | atlascloud | vercel | openrouter |
| messages | object[] | Yes | OpenAI-format messages, each with role and content. |
| stream | boolean | No | true returns an SSE stream. |
| max_tokens | integer | No | Output token cap; credits are pre-held for it (default 4096). |
Output
This example uses stream: false. Read the reply from choices[0].message.content. With stream: true, read SSE chunks from choices[].delta until [DONE].
Task completed
{
"id": "chatcmpl-example",
"object": "chat.completion",
"model": "gemini-4-argon",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 8,
"total_tokens": 17
}
}Response fields
| Name | Type | Required | Description |
|---|---|---|---|
| id | string | Yes | Chat completion ID |
| object | string | Yes | chat.completion |
| model | string | Yes | gemini-4-argon |
| choices | object[] | Yes | Reply choices; message.content contains the non-streaming response. |
| usage | object | No | Token usage: prompt_tokens, completion_tokens and total_tokens. Availability depends on the provider. |
Model schema
This public endpoint returns the model parameters and each provider’s supported constraints and prices.
curl "https://01router.com/api/v1/models/gemini-4-argon"Errors
Check the HTTP status and error.message. Fix the request before retrying validation or authentication errors. A failed generation is reported in status and error on the task itself.
{
"error": {
"message": "Invalid or missing API key",
"code": "unauthorized"
}
}400Invalid body or parameter value
401Missing or invalid API key
402Not enough credits
404Unknown model or generation
429Too many requests — retry after the given seconds
502Every provider rejected the task (credits refunded)
Use with AI
Give your coding assistant this model reference: endpoints, input constraints, output fields and request examples in plain text.
How does Gemini 4 Argon compare?
Specs and starting prices side by side. Test with the same prompt before you choose.
| Gemini 4 Argon | Gemini 3.8 Flash | GPT-6 Astra | GPT-6 Sol | |
|---|---|---|---|---|
| Vendor | OpenAI | OpenAI | ||
| Starting price | $0.72 / 1M input tokens | $0.203 / 1M input tokens | $2.52 / 1M input tokens | $0.54 / 1M input tokens |
| Input | Text | Text | Text | Text |
| Provider | 7 providers | 7 providers | 7 providers | 7 providers |
Gemini 4 Argon API FAQ
What is Gemini 4 Argon?
Google's flagship model for reasoning, agentic coding, long outputs and multimodal work across text, images, audio, video and PDFs.
Does the 1M figure mean context or output?
Context. Argon has about 1,048,576 tokens of context shared by input, thinking and output; a single response returns up to about 65K tokens.
How do thinking levels work?
Choose low, medium or high. Higher levels reason longer on hard tasks; thinking tokens are billed at the output rate.
Does it support tools and structured output?
Yes, function calling and structured JSON output are supported, and responses can stream.
How is it billed on 01router?
Per 1M input and output tokens. Google's introductory pricing may change, so check the pricing table on this page for the current rate.
Related models
Other models you can call with the same API key.
Gemini 3.8 Flash
Google Gemini 3.8 Flash: fast, low-cost multimodal model with a 1M-token context.
GPT-6 Astra
OpenAI GPT-6 Astra: the most capable GPT-6 tier for hard reasoning, coding and agents. 1.05M context.
GPT-6 Sol
OpenAI GPT-6 Sol: balanced GPT-6 tier for everyday reasoning, coding and tool use. 1.05M context.
GPT-6 Luna
OpenAI GPT-6 Luna: the fastest, lowest-cost GPT-6 tier for high-volume tasks. 1.05M context.
GPT-5.6 Sol
OpenAI GPT-5.6 Sol: flagship GPT-5.6 tier for complex reasoning and coding.
GPT-5.6 Terra
OpenAI GPT-5.6 Terra: mid GPT-5.6 tier balancing quality and cost.