Compare

Grok 4.7 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
Grok 4.7
xai/grok-4.7
Decisions
openai/decisions
Provider
xAI
OpenAI
Family
Grok 4
Modality
text
text
Context window
500,000 tok
1,050,000 tok
Max output
32,768 tok
32,768 tok
Released
2026-09-22
2026-10-26
License
Proprietary
Open-weight
Input price
$2.00 /1M
$0.100 /1M
Output price
$6.00 /1M
$0.0000 /1M
Tools
—
—
Streaming
yes
yes
Vision
yes
—
JSON mode
—
—
Reasoning
—
—
Prompt caching
—
—
Batch API
—
—
Try it
Open in playground →
Open in playground →
Grok 4.7
xai/grok-4.7
Full spec →

xAI's Grok 4.7, a frontier reasoning model for coding, agentic tasks, and knowledge work. Accepts text and image inputs, and supports function calling, structured outputs, and configurable reasoning effort (low, medium, high, xhigh).

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 Grok 4.7
google/gemini-4-argon · xai/grok-4.7
Gemini 4 Argon vs Decisions
google/gemini-4-argon · openai/decisions
Claude Opus 5.5 vs Grok 4.7
anthropic/claude-opus-5.5 · xai/grok-4.7
Claude Opus 5.5 vs Decisions
anthropic/claude-opus-5.5 · openai/decisions
Claude Sonnet 5.5 vs Grok 4.7
anthropic/claude-sonnet-5.5 · xai/grok-4.7
Claude Sonnet 5.5 vs Decisions
anthropic/claude-sonnet-5.5 · openai/decisions
Deepseek-V4.1-Flash-1017 vs Grok 4.7
deepseek/deepseek-v4.1-flash-1017 · xai/grok-4.7
Deepseek-V4.1-Flash-1017 vs Decisions
deepseek/deepseek-v4.1-flash-1017 · openai/decisions
Grok 4.7 vs MiniMax M3.1 Flash
xai/grok-4.7 · minimax/m3.1-flash
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-...",
)

# Grok 4.7
client.chat.completions.create(
    model="xai/grok-4.7",
    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 →