xAI · in Borg

Grok 4.6

Grok 4.6 follows 4.5, with xAI emphasizing sustained agents, multi-step research and more polished interactive or visual software projects.

Reasoning500,000 tokenstext, image

500,000 tokensContext window

3252 msMedian time to first token (gateway proxy)

13.6Output tokens per second (whole turn)

$2 / $6Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Specification	Value
Provider	xAI
Family	Grok
Release date	2026-08-12 Vendor source
Context window	500,000 tokens Vendor source
Input modalities	text, image
Output modalities	text
Reasoning	Yes
Open weights	No
Borg lane ids	`grok-4.6`, `x-ai/grok-4.6`
Versions in Borg	Grok 4.3 · Grok 4.5 · Grok 4.6 · Grok 4.7
Median time to first token (gateway proxy) on Borg	3252 ms
Median tokens per second (end to end) on Borg	13.6 output tokens per second

Not published by the vendor: thinking modes, knowledge cutoff, fusion roles.

What Grok 4.6 is good for

Grok 4.6 follows 4.5, with xAI emphasizing sustained agents, multi-step research and more polished interactive or visual software projects. Its adjustable reasoning and tool support suit codebase changes that require several cycles of investigation, implementation and checking. It accepts images for interpreting a design mockup or screenshot, but produces text rather than rendered media. Relative to 4.5, the vendor describes stronger long-running work and visual first passes; relative to 4.7 it is the earlier frontier generation at the same standard token price. It is a useful fixed choice for evaluating that balance on engineering tasks without assuming it has 4.7's newer base model. Borg includes Grok 4.6 in the subscription; pick its lane directly or let Borg Fusion choose it for appropriate requests.

multi-step codebase changes
interactive application prototyping
agent-led research and verification
visual UI iteration from screenshots

How Borg uses it

Grok 4.6 is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.

model: "grok-4.6"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	3252 ms	51032 ms	3471
Tokens per second (end to end)	13.6 output tokens per second	54.4 output tokens per second	32690

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Grok 4.63252 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Grok 4.613.6 tokens/s

Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate

Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 34616 requests. Minimum 100 samples per published request metric.

Benchmarks

Benchmark	Vendor-reported score	Source
CursorBench v3.2	69.9%	Vendor source
DeepSWE v1.1	65.9%	Vendor source
FrontierCode v1.1 (Extended)	61.3%	Vendor source
APEX-Agents	57.5%	Vendor source
Terminal-Bench v3.0	26%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $2 input / $6 output per 1M tokens. Vendor price source.

Global rates for prompts below 200,000 input tokens. At 200,000 input tokens or more, all tokens use long-context rates: $4 input / $12 output / $1 cached input per 1M tokens. US regional inference costs 1.1× the global rate. Vendor pricing terms

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Grok 4.6?

Grok 4.6 is listed in Borg's subscription catalog as grok-4.6. Grok 4.6 follows 4.5, with xAI emphasizing sustained agents, multi-step research and more polished interactive or visual software projects.

Is Grok 4.6 in Borg?

Yes. Grok 4.6 is listed in Borg's subscription catalog under the lane grok-4.6. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.

What context window does Grok 4.6 have?

The published context window is 500,000 tokens. Consult the cited sources for details and current limits. Vendor source

Is Grok 4.6 good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include multi-step codebase changes, interactive application prototyping, agent-led research and verification, visual UI iteration from screenshots. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Grok 4.6 on Borg?