The Orchestrator › Models › Google

Google: Gemini 4 Argon

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...

Specifications

ProviderGoogle
Model IDgoogle/gemini-4-argon
Context window1.0M tokens (1,048,576)
Modalitiestext + image + file + audio + video → text
TokenizerGemini
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-10-13
Tracked since2026-11-14
Popularity#22 by usage · peak 6.8% spend share in an OpenRouter category
ReasoningMandatory

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRoutergoogle/gemini-4-argon$2.00$10.001.0M
batchOpenRoutergoogle/gemini-4-argon:batch$1.00$5.001.0M
standardTrustedRoutergoogle/gemini-4-argon$2.11$10.551.0M
standardVercel AI Gatewaygoogle/gemini-4-argon$2.00$10.001M
standardCloudflaregoogle/gemini-4-argon$2.00$10.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$2.00$10.00—
2026-11-14$2.00$10.001M
2026-11-14$2.11$10.551.0M
2026-11-14$2.00$10.001.0M

Capabilities

Vision (image input)Audio inputVideo inputFile inputAgentic tool useStructured outputsReasoning (always on)1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)

Trust flags come from TrustedRouter's per-provider attestations.

Supported parameters

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