theserverless.dev InferenceList

Models / Google

Google: Gemini 4 Argon

google/gemini-4-argon

audio text image videoContext 1.0M

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

Price

Input$2

per 1M tokens

Output$10

per 1M tokens

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
Google AI Studio google-ai-studio/flex — $1/1M $5/1M 1.0M 100% Live openrouter-endpoints
AtlasCloud — fp8 $1.6/1M $8/1M 1.0M — Listed atlascloud
Google google-vertex/global — $2/1M $10/1M 1.0M 100% Live openrouter-endpoints
Google AI Studio google-ai-studio — $2/1M $10/1M 1.0M 100% Live openrouter-endpoints
Google google-vertex/us — $2.2/1M $11/1M 1.0M 100% Live openrouter-endpoints
Venice — — $2.5/1M $12.5/1M 1M — Listed venice
Google google-vertex/global/priority — $3.6/1M $18/1M 1.0M — Live openrouter-endpoints
Google AI Studio google-ai-studio/priority — $3.6/1M $18/1M 1.0M 100% Live openrouter-endpoints

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$12.00 at list price for this workload

Cache

Cache read$0.1

per 1M tokens

Cache write$0.1875

per 1M tokens

Tiers

Web search
$0.014 per request
Image input
$2 per 1M tokens
Audio
$2 per 1M tokens
Audio cache
$0.1 per 1M tokens
Reasoning
$10 per 1M tokens
Every rate
UnitInputOutputFlatConfidence
token $2/1M $10/1M Not published— official

Price history

Google: Gemini 4 Argon
15 0 2026-10-13: $22026-10-14: $22026-10-15: $22026-10-16: $22026-10-17: $22026-10-18: $22026-10-19: $22026-10-20: $22026-10-21: $22026-10-22: $22026-10-23: $22026-10-24: $22026-10-25: $22026-10-26: $22026-10-27: $22026-10-28: $22026-10-29: $22026-10-30: $2 2026-10-13 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-10-13 token $2 $10 Not published—
2026-10-14 token $2 $10 Not published—
2026-10-15 token $2 $10 Not published—
2026-10-16 token $2 $10 Not published—
2026-10-17 token $2 $10 Not published—
2026-10-18 token $2 $10 Not published—
2026-10-19 token $2 $10 Not published—
2026-10-20 token $2 $10 Not published—
2026-10-21 token $2 $10 Not published—
2026-10-22 token $2 $10 Not published—
2026-10-23 token $2 $10 Not published—
2026-10-24 token $2 $10 Not published—
2026-10-25 token $2 $10 Not published—
2026-10-26 token $2 $10 Not published—
2026-10-27 token $2 $10 Not published—
2026-10-28 token $2 $10 Not published—
2026-10-29 token $2 $10 Not published—
2026-10-30 token $2 $10 Not published—

Alternatives

Parameters (12)
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Call this model

OpenRouter id google/gemini-4-argon. InferenceList does not send the request.

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

JavaScript 
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "google/gemini-4-argon",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python 
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "google/gemini-4-argon", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON