Compare

Gemini 4 Argon vs Decisions

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Gemini 4 Argon
google/gemini-4-argon
Decisions
openai/decisions
Provider
Google
OpenAI
Family
Modality
text
text
Context window
1,048,576 tok
1,050,000 tok
Max output
65,536 tok
32,768 tok
Released
2026-10-14
2026-10-26
License
Proprietary
Open-weight
Input price
$2.00 /1M
$0.100 /1M
Output price
$10.00 /1M
$0.0000 /1M
Tools
—
—
Streaming
yes
yes
Vision
—
—
JSON mode
—
—
Reasoning
—
—
Prompt caching
—
—
Batch API
—
—
Try it
Open in playground →
Open in playground →
Gemini 4 Argon
google/gemini-4-argon
Full spec →

Google's frontier model for deep work on complex, real-world tasks across coding, finance, legal, cybersecurity and science. The first model in the Gemini 4 family.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Decisions
openai/decisions
Full spec →

Decisions uses GPT-6 Luna to evaluate shared text or image evidence against typed questions. It returns probabilities, fixed choices, or rubric scores for low-latency classification, routing, and prioritization workflows.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Gemini 4 Argon vs Claude Opus 5.5
google/gemini-4-argon · anthropic/claude-opus-5.5
Gemini 4 Argon vs Claude Sonnet 5.5
google/gemini-4-argon · anthropic/claude-sonnet-5.5
Gemini 4 Argon vs Deepseek-V4.1-Flash-1017
google/gemini-4-argon · deepseek/deepseek-v4.1-flash-1017
Gemini 4 Argon vs Grok 4.7
google/gemini-4-argon · xai/grok-4.7
Gemini 4 Argon vs MiniMax M3.1 Flash
google/gemini-4-argon · minimax/m3.1-flash
Gemini 4 Argon vs Qwen3.8-Max
google/gemini-4-argon · alibaba/qwen3.8-max
Gemini 4 Argon vs GLM-5.3-Prime
google/gemini-4-argon · zai-org/glm-5.3-prime
Gemini 4 Argon vs Pareto
google/gemini-4-argon · unbiased/pareto
Gemini 4 Argon vs Jev 1.14
google/gemini-4-argon · typesafe/jev-1.14.0
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Gemini 4 Argon
client.chat.completions.create(
    model="google/gemini-4-argon",
    messages=[{"role":"user","content":"hello"}],
)

# Decisions
client.chat.completions.create(
    model="openai/decisions",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →