ModelPickr

Models / xAI / Grok 4.3

xAI · grok

Grok 4.3

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

$1.25 in · $2.50 out

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

Provider input prices run from $1.25 to $1.42 per 1M tokens. Output prices run from $2.50 to $2.83.

Context
1,000,000
Max output
30,000
Cache read
$0.20
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Apr 17, 2026
Updated in source
Apr 17, 2026
Knowledge
—
Providers
27

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$1.25$2.50———
Abacus$1.25$2.50$0.20——
Amazon Bedrock$1.25$2.50$0.20——
Auriko$1.25$2.50$0.20——
Cloudflare AI Gateway$1.25$2.50$0.20——
CrossModel$1.25$2.50$0.20$1.25—
DaoXE$1.25$2.50$0.20——
DevPass$1.25$2.50$0.20——
Eden AI$1.25$2.50$0.20——
FastRouter$1.25$2.50———
Impossibl$1.25$2.50$0.20——
Kilo Gateway$1.25$2.50$0.20——
Merge Gateway$1.25$2.50$0.20——
NanoGPT$1.25$2.50$0.20——
OCI Generative AI$1.25$2.50$0.20——
Ofox$1.25$2.50$0.20——
OpenRouter$1.25$2.50$0.20——
Opper$1.25$2.50$0.20——
OrcaRouter$1.25$2.50$0.20——
Requesty$1.25$2.50$0.20$1.25—
Tempr Gateway$1.25$2.50$0.20——
Vercel AI Gateway$1.25$2.50$0.20——
Vertex$1.25$2.50$0.20—beta
xAIreference$1.25$2.50$0.20——
ZenMux$1.25$2.50$0.20——
Venice AI$1.42$2.83$0.23——
AnyAPI—————

Jobs this model qualifies for