Inkling vs Grok 4.3

API pricing, benchmark indices and specs — updated 19 October 2026.

thinkingmachines · A · Open weights

Params

952.4 B

Context

—

30d

1.4 M

apache-2.0 · commercial OK

x-ai · B · API-only

Input / 1M

$1.25

Output / 1M

$2.50

AA index

24.9

proprietary · 1M context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Inkling	Grok 4.3
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	952.4 B	n/a — API-only
Architecture	InklingForConditionalGeneration	n/a — API-only
Context length	524,288	1,000,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	—	n/a — API-only
Downloads 30d	1,422,701	n/a — API-only
Downloads all time	2.0 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2026-07-14	n/a — API-only
API input price / 1M tokens	$1.00	$1.25
API output price / 1M tokens	$4.05	$2.50
Est. cost per 1M input + 1M output tokens	$5.05	$3.75
Cached input / 1M tokens	$0.17	$0.20
AA Intelligence Index	25	24.9
AA Coding Index	52.1	42.2
AA Agentic Index	22.5	15.5
Max output tokens	471,859	900,000
API providers	1	1
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

Inkling $5.05

Grok 4.3 $3.75

Grok 4.3 is 1.3× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Inkling · fp16 2,238.6 GB / 24 GB

❌ Won’t fit