Context
524K
Max output
524K
Serving providers
8
Cheapest input
$2.00 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
56 t/s
tokens / second
Time to first token
43.86s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.4 | default | — | |||||||||||||||||
| Automation Bench | 0.7 | default | — | |||||||||||||||||
| CritPt | 17% | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1747.5 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 95% | default | — | |||||||||||||||||
| Humanity's Last Exam | 43% | default | — | |||||||||||||||||
| Long-Context Reasoning | 80% | default | — | |||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||
| Omniscience | 30.5 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.5 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.7 | default | — | |||||||||||||||||
| SciCode | 56% | default | — | |||||||||||||||||
| Terminal Bench40 | 0.2 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 88% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 51% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing detail
cost beyond the standard rate · source: models.devLong context (>200K)
$4.53 / $13.60
input / output · per 1M
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $2.00 to $2.50 per 1M tokens across 8 providers, so the dearest route costs 25% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aihubmix | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardaihubmix/grok-4.6
| |||||||||||||||||||
| Azure | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardazure_ai/grok-4.6
| |||||||||||||||||||
| Amazon Bedrock | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardglobal.xai.grok-4.6
| |||||||||||||||||||
| OpenRouter | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardx-ai/grok-4.6
| |||||||||||||||||||
| VercelVercel reseller quote | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardspacexai/grok-4.6
| |||||||||||||||||||
| Vertex AI | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardvertex_ai/xai/grok-4.6
| |||||||||||||||||||
| xAICheapest | $2.00 | $6.00 | 1 | ||||||||||||||||
Standardxai/grok-4.6
| |||||||||||||||||||
| Databricks | $2.50 | $7.50 | 1 | ||||||||||||||||
Standarddatabricks/databricks-grok-4-6
| |||||||||||||||||||
| Vercel is dearest at $4.00 / $12.00 | |||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$880
estimated / month
Model IDs
copy the exact identifier for your platformx-ai/grok-4.6global.xai.grok-4.6xai/grok-4.6vertex_ai/xai/grok-4.6aihubmix/grok-4.6spacexai/grok-4.6azure_ai/grok-4.6databricks/databricks-grok-4-6spacexai/grok-4.6spacexai/grok-4.6
Frequently asked questions
Grok 4.6 pricing, context and availabilityHow much does Grok 4.6 cost?
Grok 4.6 costs $2.00 per 1M input tokens from xAI, and $6.00 per 1M output tokens from xAI. Across 8 serving providers, input prices range from $2.00 to $2.50 per 1M tokens.
What is the context window of Grok 4.6?
Grok 4.6 accepts up to 524K tokens of context and can return up to 524K output tokens.
Which providers serve Grok 4.6?
Grok 4.6 is available from 8 serving providers, each with its own pricing and model ID. xAI is currently the cheapest.
What can Grok 4.6 do?
Grok 4.6 supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other xAI models
compare pricing across the xAI lineupGrok 4$1.25/1M · 6 providersGrok 4.3$1.25/1M · 6 providersGrok 4.7$2.00/1M · 6 providersGrok 4 20 Non Reasoning$1.25/1M · 5 providersGrok 4 20 Reasoning$1.25/1M · 5 providersGrok 4.1 Fast Non Reasoning$0.20/1M · 4 providersGrok 4.1 Fast Reasoning$0.20/1M · 4 providersGrok 3 Mini$0.25/1M · 4 providers
Popular comparisons
head-to-head pages featuring Grok 4.6
Grok 4.6 vs Claude Fable 5.1side-by-side pricing & benchmarks Grok 4.6 vs Claude Opus 5side-by-side pricing & benchmarks
Grok 4.6 vs DeepSeek V4.1 Flashside-by-side pricing & benchmarks Grok 4.6 vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Grok 4.6 vs Gemini 3.7 Flashside-by-side pricing & benchmarks Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI