Grok 4.6 pricing & benchmarks
Grok 4.6 is available from SpaceXAI at $2.00 per million input tokens and $6.00 per million output tokens ($3.00 blended at 3:1). It accepts up to 500,000 tokens of context. Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
Pricing
Per million tokens · OpenRouter
Input$2.00
Output$6.00
Blended (3:1)$3.00
Specification
x-ai/grok-4.6
Context window500K
Max output450K
ReleasedAug 2026
LicenceProprietary
Modalitiesin:text, in:image, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 94.0% ±1.4 | high effort | 2026-08-12 | Independently run · Epoch AI |
| FrontierMath T1–3 | 66.0% ±2.8 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
| FrontierMath T4 | 31.7% ±7.4 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
| OTIS Mock AIME | 99.2% ±0.5 | xhigh effort | 2026-08-14 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| Gemini 3.7 Flash | $1.50 (−50%) | 94.8% | Compare → | |
| Gemini 3.6 Flash | $1.50 (−50%) | 94.1% | Compare → |
Where to run Grok 4.6
6 options across 2 providers · 2.0× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| xAI (zdr) ⚠ re-prices above 200K prompt tokens ($4.00/$12.00) |
$3.00 | $2.00 / $6.00 | 500K | 100.0% |
| xAI ⚠ re-prices above 200K prompt tokens ($4.00/$12.00) |
$3.00 | $2.00 / $6.00 | 500K | 100.0% |
| xAI (zdr/us) ⚠ re-prices above 200K prompt tokens ($4.40/$13.20) |
$3.30 | $2.20 / $6.60 | 500K | 100.0% |
| Amazon Bedrock (us-west-2) ⚠ re-prices above 200K prompt tokens ($4.40/$13.20) |
$3.30 | $2.20 / $6.60 | 500K | 100.0% |
| xAI (zdr/priority) ⚠ re-prices above 200K prompt tokens ($8.00/$24.00) |
$6.00 | $4.00 / $12.00 | 500K | — |
| xAI (priority) ⚠ re-prices above 200K prompt tokens ($8.00/$24.00) |
$6.00 | $4.00 / $12.00 | 500K | — |
Host prices and uptime from OpenRouter, synced 2026-10-22.
Subscriptions that include Grok 4.6
Consumer plans whose published model list names this model
Compare Grok 4.6
FAQ
How much does Grok 4.6 cost?
Grok 4.6 costs $2.00 per million input tokens and $6.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $3.00 per million tokens.
What is Grok 4.6's context window?
Grok 4.6 accepts up to 500,000 tokens of context, and can generate up to 450,000 output tokens.
How good is Grok 4.6 on benchmarks?
Grok 4.6 scores 94.0% on GPQA Diamond, independently run and published by Epoch AI. 4 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Grok 4.6?
Yes — 2 models in our catalogue cost less per token than Grok 4.6 and score at least as high on the same benchmark. The cheapest is Gemini 3.7 Flash at $1.50 per million tokens blended.