GOOGLE MODEL GUIDE

Gemini 4 Argon API

Gemini 4 Argon is Google's reasoning model for complex code migrations, research, and work that needs several stages of analysis.

Get API Key Model pricing calculator View Docs

Core specificationsModel Plaza checked November 10, 2026

Model IDgemini-4-argon

Context / max output1,048,576 / 65,536 / 32,768

Input and outputText, image, video, audio and PDF input; text output

ThinkingLOW / MEDIUM / HIGH

Vendor statusActive

LLMFly AI input / output per 1M$0.8 / $4 (60% OFF)

Selection verdictGemini 4 Argon bills at $0.8 input / $4 output per 1M tokens on LLMFly AI (0.4x standard tier).

Best fit

For a repository migration, test dependency changes, generated patches, and the resulting build. Use Gemini 3.8 Flash as a baseline for smaller tasks.

Avoid when

Workflows that depend on explicit caching in Google's native API.

Gemini API cost estimate

Enter token counts for one representative request; every usage item is multiplied by the request count.

Gemini0.4xCurrent multiplier

Estimated LLMFly AI cost$0.12Gemini 4 Argon · 1 request

Vendor reference cost$0.30Estimated savings$0.1860.0%

Cost breakdown

Rates are per 1M tokens

Input$0.08

LLMFly AI: $0.8
Vendor reference: $2
Total tokens: 100,000

Output$0.04

LLMFly AI: $4
Vendor reference: $10
Total tokens: 10,000

Cache write—

LLMFly AI: —
Vendor reference: —
Total tokens: 0

Cache read$0.00

LLMFly AI: $0.04
Vendor reference: $0.1
Total tokens: 0

Choosing and integrating

Gemini 4 Argon API pricing breakdown

Gemini 4 Argon (gemini-4-argon) is billed by token usage. Prices below are USD per 1M tokens. LLMFly AI rates already include the 0.4x group multiplier; do not apply it again. Provider reference prices are separate. These rates come from the site's Model Plaza snapshot; confirm live catalog and account rates before calling.

Example: a request with 10,000 uncached input tokens and 1,000 output tokens costs approximately $0.012 in LLMFly AI token charges. This excludes cache writes, tools, retries, and other additional fees.

Platform and provider prices use their own input-token tiers. Do not apply provider long-context multipliers to platform prices.
Not listed does not mean free. Account for cache reads, cache writes, and uncached input in their respective billing categories.
Token cost = tokens in each billing category × its price per million ÷ 1,000,000. Add tools and other charges separately.

Price source	Input tokens per request	Input	Output	Cache write	Cache read	1h cache write
LLMFly AI	Single rate	$0.8	$4	Not listed	$0.04	Not listed
Provider reference	Single rate	$2	$10	Not listed	$0.1	Not listed

Pricing tiers and additional charges

Google lists introductory Standard rates through November 30, 2026. From December 1 its published rates are $4 input, $20 output, and $0.20 cached input per million tokens. Check LLMFly AI rates separately.

Gemini 4 Argon capabilities and workloads

Google counts input, reasoning, tool calls, and final text against one shared context limit. Native foreground output is capped at 65,536 tokens with streaming or 32,768 without it.

Limits to check before migration

When migrating from Flash, replace thinking_budget with a supported thinking level. Verify long output and implicit cache hits on your actual route.

Comparing Gemini 4 Argon with sibling models

For a repository migration, test dependency changes, generated patches, and the resulting build. Use Gemini 3.8 Flash as a baseline for smaller tasks.

Model ID	Context / max output	LLMFly AI in / out	Vendor reference in / out
gemini-4-argon	1,048,576 / 65,536 / 32,768	$0.8 / $4	$2 / $10
gemini-2.5-pro	1,048,576 / 65,536	$0.5 / $4	$1.25 / $10
gemini-3.8-flash	1,048,576 / 65,536	$0.3 / $1.5	$0.75 / $3.75
gemini-3.7-flash	1,048,576 / 65,536	$0.3 / $1.5	$0.75 / $3.75
gemini-3.6-flash	1,048,576 / 65,536	$0.3 / $1.5	$0.75 / $3.75

Use the exact model ID when connecting

Set LLMFLY_API_KEY to a key with access to this model, then send this text request.

Send a minimal text request and inspect the response and usage.
Test streaming, tool calls, and structured output separately if your application needs them.
Check retry behavior and spending limits before increasing traffic.

request.example

curl https://app.llmfly.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMFLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-4-argon",
  "messages": [
    {
      "role": "user",
      "content": "Reply with OK."
    }
  ],
  "stream": false
}'

Vendor capability versus gateway access

Gemini 4 Argon runs under the Gemini group (0.4x multiplier) in Model Plaza over the OpenAI-compatible https://app.llmfly.ai/v1/chat/completions endpoint. Validate provider-specific tools or grounding parameters on your route and reconcile billed tokens in your console usage log.

Frequently asked questions

What should I put in the model field?

Use the exact ID gemini-4-argon, not the display name.

How is the discount calculated?

The current 0.4x multiplier is applied to the base rate, giving 60% off the catalog's official reference. Amounts are shown per million tokens.

Do these prices include every possible fee?

Not necessarily. Check cache-write duration, tools, and other route charges separately. Use the full pricing table and actual usage records to reconcile a bill.

What are the context and output limits?

Vendor documentation lists 1,048,576 context and 65,536 / 32,768 maximum output; confirm gateway route limits separately.

Use the Gemini 4 Argon API

LLMFly AI provides this model. Use the exact ID gemini-4-argon and confirm current account pricing in Model Plaza.

View model and rates