Models / xAI / Grok 4.5

xAI · grok

Grok 4.5

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

$2.00 in · $6.00 out

per 1M tokens · first-party price. Reference price from xAI, the lab's own listing.

Provider input prices run from $2.00 to $2.27 per 1M tokens. Output prices run from $6.00 to $6.80.

Context
500,000
Max output
500,000
Cache read
$0.30
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Jul 8, 2026
Updated in source
Jul 8, 2026
Knowledge
—
Providers
26

Higher rates apply above 200,000 input tokens. The calculator switches to that rate when the input is longer.

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
302.AI$2.00$6.00———
Abacus$2.00$6.00———
AIHubMix$2.00$6.00$0.50——
Cloudflare AI Gateway$2.00$6.00$0.30——
CrossModel$2.00$6.00$0.30$2.00—
DaoXE$2.00$6.00$0.50——
Eden AI$2.00$6.00$0.30——
GitHub Copilot$2.00$6.00$0.50——
Impossibl$2.00$6.00$0.30——
Kilo Gateway$2.00$6.00$0.30——
Merge Gateway$2.00$6.00$0.50——
NanoGPT$2.00$6.00$0.50——
Ofox$2.00$6.00$0.30——
OpenCode$2.00$6.00$0.30——
OpenCode Go$2.00$6.00$0.30—deprecated
OpenRouter$2.00$6.00$0.30——
Opper$2.00$6.00$0.50——
OrcaRouter$2.00$6.00$0.50——
Pioneer$2.00$6.00$0.50$2.00—
Requesty$2.00$6.00$0.50$2.00—
Tempr Gateway$2.00$6.00$0.30——
Vercel AI Gateway$2.00$6.00$0.30——
xAIreference$2.00$6.00$0.30——
ZenMux$2.00$6.00$0.50——
Venice AI$2.27$6.80$0.34——
Kenari$0$0———

Jobs this model qualifies for