TokenRoute
Get started
Back to models

Google: Gemini 4 Argon (batch)

google/gemini-4-argon:batch

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...

Try in Playground

Pricing

Input$0.7000 /M
Output$3.50 /M
Reasoning$3.50 /M
Cache read$0.0350 /M
Cache write$0.1312 /M
Image$0.00000 /image
Web search$0.0098 /req

Specs

Context length1M tokens
Max output943.7K tokens
Inputaudio, file, image, text, video
Outputtext

Quickstart

Point the OpenAI SDK at https://tokenroute.app/api/v1 and use a TokenRoute API key.

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

Supported parameters

include_reasoning
max_tokens
reasoning
reasoning_effort
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p