How much does Gemini 4 Argon cost?

On the Respan gateway, Gemini 4 Argon costs from $1.00 per 1M input tokens and $5.00 per 1M output tokens on Google Gemini AI, after gateway discounts. Averaged across its 2 providers, it costs $1.50 per 1M input tokens and $7.50 per 1M output tokens.

Which providers serve Gemini 4 Argon on Respan?

Gemini 4 Argon is available through 2 providers: Google Gemini AI and OpenRouter.

What is Gemini 4 Argon's context window?

Gemini 4 Argon accepts up to 1M tokens of context on its largest provider route.

How do I use Gemini 4 Argon with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemini/gemini-4-argon". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Gemini 4 Argon?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Google Gemini AI at 9 tokens per second, and the lowest response latency was 2.5 seconds on Google Gemini AI. Speed varies with request size and provider.

Where does Gemini 4 Argon rank on the Respan Index?

Gemini 4 Argon scores 71.4 out of 100 on the Respan Index v1.1, ranking #2 of 143 models. By category: Coding 64.4, Agents 80.2, Reasoning 78.4, Knowledge & language 70.1 (estimated), and Human preference 57.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Gemini 4 Argon score on benchmarks?

Gemini 4 Argon has 12 published benchmark scores, including DeepSWE v1.1 77.9%, APEX-Agents 82.2%, and LVBench 91.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Gemini 4 Argon

Q: What is Gemini 4 Argon?

Gemini 4 Argon is a model from Google Gemini AI, released on Oct 13, 2026. Google flagship reasoning model for software engineering, agents, mathematics and science. Shared 1048576-token input, thinking and output window.

Google flagship reasoning model for software engineering, agents, mathematics and science. Shared 1048576-token input, thinking and output window.

Input / output, fromSave up to 50%: $1.00 / $5.00 per 1M
Context: 1M tokens
Released: Oct 13, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gemini/gemini-4-argon".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="gemini/gemini-4-argon",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "gemini/gemini-4-argon",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "gemini/gemini-4-argon",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Google Gemini AISave 50%`gemini/gemini-4-argon`	1M	$1.00/M	$5.00/M	$0.05/M	+2
OpenRouter`openrouter/google/gemini-4-argon`	1M	$2.00/M	$10.00/M	$0.10/M	+2

Is a provider down? Google AI status, OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $1.50 per 1M
Average output: $7.50 per 1M
Average cache read: $0.08 per 1M
Average cache write: $0.09 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$2.00/MOpenRouterLowest$1.00/MGoogle Gemini AI

Throughput and latency

30-day averages from requests through the Respan gateway, 1 of 2 routes had traffic in that window. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

8.8tokens/son Google Gemini AI

Faster than 18% of the other 483 models on the gateway

Time to first token

Lower is better

1.5son Google Gemini AI

Faster than 68% of the other 63 models on the gateway

Response latency

Lower is better

2.5son Google Gemini AI

Faster than 36% of the other 484 models on the gateway

No traffic in the last 30 days on OpenRouter.

Benchmarks

The Respan Index plus 12 published scores from 6 sources, each linked to where it was published.

71.4/ 100

Respan Index#2 of 143

143 ranked models. The shaded band is this model's 95% interval, 49.7 to 79.8. Claude Opus 5.5 and GPT-6 Astra fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
DeepSWE v1.1Google	77.9%	Google	Sep 30, 2026
CWE-bench v1Google	68%	Google	Sep 30, 2026
Terminal-Bench 4.0Vals AI	57.6%	Vals AI	Oct 5, 2026
FrontierSWE V2Proximal Labs	55%	Proximal Labs	Oct 5, 2026

Benchmark	Score	Source	Published
APEX-AgentsMercor	82.2%	Mercor	Oct 5, 2026
AutomationBenchGoogle	51.3%	Google	Sep 30, 2026
Vending-Bench 2Andon Labs	13718.16 · #3 of 59	Andon Labs	Oct 5, 2026

Benchmark	Score	Source	Published
LVBenchGoogle	91.7%	Google	Sep 30, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1678 Elo · #8 of 99	LMArena	Oct 8, 2026
LMArena EloLMArena	1525 Elo · #1 of 147	LMArena	Oct 8, 2026
LMArena AgentLMArena	0.1237 · #4 of 51	LMArena	Oct 12, 2026