low · medium · high · xhigh · default high
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / XAI
Grok 4.6
verified model reference.
xAI frontier reasoning model for coding, agentic work, and long-context knowledge tasks.
500,000context tokens
No separate limitmax output
2026-10-03last verified
PRIMARY-SOURCE VERIFIED
Grok 4.6 at a glance.
xAI documents a 500,000-token context window. Input modalities: text + image. Output: text. Pricing status: Official paid API.
MODEL IDgrok-4.6
CONTEXT WINDOW500,000tokens
MAX OUTPUTNo separate limit
KNOWLEDGE CUTOFF2026-02-01
STANDARD INPUT$2.00official-paid
STANDARD OUTPUT$6.00official-paid
CAPABILITY CONTRACT
Published model behavior.
text + image
Input modalities come from the cited official model documentation.
text
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Official paid API.
$2.00 input · $0.50 cached · $6.00 output / MTok.
Only provider-published Standard paid token rates enter the SXF calculator. Partner hosting prices, negotiated rates and self-hosting costs are not substituted for a missing provider rate.
CAVEATS
What the source record does not assume.
01
xAI documents no separate text output limit for Grok 4.6.
02
Higher long-context token rates apply when prompt tokens exceed 200,000.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
Grok 4.6: what changed.
No post-baseline factual changes recorded for Grok 4.6 since 2026-10-03.
VERIFIED BASELINE2026-10-03Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
Grok 4.6 verified history.
Grok 4.6
Baseline verified: 500,000 context · No separate limit max output · $2.00 input / $6.00 output per MTok
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head c62519fdffa4…
COMPARE GROK 4.6