xAI: Grok 4.6

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Source-linked grok Closed weights Released 2026-08-12

API record Report

InputT

OutputT

Input price$2/M

Output price$6/M

Context500K

Max output500K

Providers30

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Grok 4.6
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Azure	`grok-4.6`	200K	128K	—	—	—	ReasoningToolsJSON	Docs ↗
Kenari	`grok-4-6`	500K	500K	—	—	—	ReasoningToolsJSON	Docs ↗
Neon	`grok-4-6`	500K	524.288K	—	—	—	ReasoningToolsJSON	Docs ↗
NanoGPT	`x-ai/grok-4.6`	500K	450K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Eden AI	`xai/grok-latest`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Eden AI	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Vertex	`xai/grok-4.6`	524.288K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Perplexity Agent	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`x-ai/grok-4.6`	500K	450K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Abacus	`grok-4.6`	500K	32.768K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
OpenRouter	`x-ai/grok-4.6`	500K	450K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
302.AI	`grok-4.6`	500K	500K	$2	$6	—	ReasoningToolsJSON	Docs ↗
OpenCode Go	`grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Requesty	`grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
OrcaRouter	`grok/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`spacexai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Ofox	`x-ai/grok-4.6`	500K	65.536K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
AIHubMix	`grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Opper	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Cloudflare AI Gateway	`grok/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
CrossModel	`x-ai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Merge Gateway	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Cloudflare AI Gateway	`xai/grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
DevPass (LLM Gateway)	`grok-4-6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
GitHub Copilot	`grok-4.6`	500K	128K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
OpenCode Zen	`grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
xAI	`grok-4.6`	500K	500K	$2	$6	$0.5	ReasoningToolsJSON	Docs ↗
Amazon Bedrock	`xai.grok-4.6`	500K	500K	$2.2	$6.6	$0.55	ReasoningToolsJSON	Docs ↗
Venice AI	`grok-4-6`	500K	200K	$2.27	$6.8	$0.57	ReasoningToolsJSON	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $2/M

Across 27 priced providers

Median input $2/M

Midpoint of listed rates

Highest input $2.27/M

1.1× the lowest listed rate

Output range $6 – $6.8

Per million output tokens

NanoGPT $2/M

Eden AI $2/M

Vertex $2/M

Perplexity Agent $2/M

Kilo Gateway $2/M

Abacus $2/M

OpenRouter $2/M

302.AI $2/M

OpenCode Go $2/M

Requesty $2/M

OrcaRouter $2/M

Vercel AI Gateway $2/M

Ofox $2/M

Vercel AI Gateway $2/M

AIHubMix $2/M

Opper $2/M

Cloudflare AI Gateway $2/M

CrossModel $2/M

Merge Gateway $2/M

Cloudflare AI Gateway $2/M

DevPass (LLM Gateway) $2/M

GitHub Copilot $2/M

OpenCode Zen $2/M

xAI $2/M

Amazon Bedrock $2.2/M

Venice AI $2.27/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

25 providers list the identical $2 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 200K to 524.288K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

✓ Structured output Yes

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: xAI
Model family: grok
Knowledge cutoff: 2026-02-01
License: Not documented
Release date: 2026-08-12
Model ID: xai/grok-4.6

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

No changes recorded

This record has not changed within the retained import history.

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/xai/grok-4.6

curl

curl "https://model.kyssta.lol/api/v1/models/xai/grok-4.6"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Grok 4.6?

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects. It is published by xAI and catalogued here from Models.dev.

How much does Grok 4.6 cost?

Listed input pricing starts at $2 per million tokens from NanoGPT, rising to $2.27 across 27 listed providers.

What is the context length of Grok 4.6?

Grok 4.6 accepts up to 500K tokens of context and returns up to 500K output tokens.

Does Grok 4.6 support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve Grok 4.6?

27 providers list this model: Azure, Kenari, Neon, NanoGPT, Eden AI, Vertex and 21 more.

Are the weights for Grok 4.6 open?

No. This model is served through hosted APIs only.

When was Grok 4.6 released?

The catalog records a release date of 2026-08-12, last verified Sep 11, 2026.

More models from xAI

View all →

Grok 4.3

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

1M ctx $1.25/M in Grok Imagine Video 1.5

Video model for image-to-video generation, editing, and extension workflows

1.024K ctx Grok Build 0.1

Fast Grok coding model tuned for agentic engineering and iterative edits

256K ctx $1/M in SpaceXAI: Grok Build 0.1

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

256K ctx $1/M in