Gemini 4 Argon API

Google's Gemini 4 Argon, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gemini-4-argon as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: gemini-4-argon
Maker: Google
Context window: 1M tokens
Input price: $1.800 per million tokens
Output price: $9.000 per million tokens
Providers: 1 independent provider
Regions: us

Providers

zro: us, $1.800 input and $9.000 output per million tokens, $0.090 cache read per million tokens, 1M tokens of context
zro: us, $1.800 input and $9.000 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context

Scores

Intelligence: 50.4, #2 of 41
HLE: 57.1, #1 of 273
AA-LCR: 79.7, #47 of 237
SciCode: 61.8, #1 of 123
SimpleQA Verified: 76.0, #1 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Gemini 4 Argon?: Gemini 4 Argon is a model from Google.
How much does Gemini 4 Argon cost?: Offers now ask $1.800 per million input tokens and $9.000 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Gemini 4 Argon?: The largest offer takes 1,048,576 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Gemini 4 Argon do?: Its providers list Reasoning effort, Log probabilities, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does Gemini 4 Argon support?: Text → Text.
Which providers serve Gemini 4 Argon?: 1 independent provider quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Gemini 4 Argon?: Send "gemini-4-argon" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Gemini 4 Argon listed?: The exchange first listed it on 10/14/2026. This is not its release date.