xAIGrok 4.6
Grok 4.6 is a multimodal chat model developed by xAI, capable of processing both text and image inputs. It demonstrates top-tier performance on several intelligence and coding benchmarks.
Input
Output
Context
500K
Max Output
-
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Benchmarks
Resources & Links
More models by xAI
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Grok 4.6
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Grok 4.6 advertises a context window of 500,000 tokens. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
No. Grok 4.6 is a proprietary model (license: Proprietary): its weights are not distributed, and it runs only through xAI's own API or a provider licensed to serve it.
Grok 4.6 accepts Text and Image and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
Grok 4.6 has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured Grok 4.6 is shown as not available rather than estimated.
Not on the managed pool today; Grok 4.6 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
Grok 4.6 cannot be self-hosted: its weights are not distributed. It is used through an API, either xAI's own or the Inferbase gateway where it is served.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Oct 16, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.