Grok 4.6 benchmarks, pricing and specs
Grok 4.6 is a xAI model released on August 12, 2026 that takes text and image input and produces text. It costs $2 per 1M input tokens and $6 per 1M output tokens and accepts up to 500,000 tokens of context. It scores 1454 Elo on Arena Text, #28 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $2
- Per 1M output tokens
- $6
- Context window
- 500K
- Arena Text
- 1454 Elo · #28/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- xAI
- Model family
- Grok 4
- Release date
- August 12, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 500,000 tokens
- Max output
- Not reported
- Input
- text, image
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning
Grok 4.6 pricing
It is the #12 most expensive of 37 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. xAI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1454 Elo | #28 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 94% | #9 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 66% | #23 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 49.3% | #19 of 34 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Grok 4.6 is positioned for coding, agentic tasks, and knowledge work; its API documentation also lists function calling and structured outputs
- xAI says it focuses on long-running agents that stay with complex tasks across many steps, with more self-testing and verification than Grok 4.5
- Epoch AI measured 94.0% on GPQA Diamond and 66.0% on FrontierMath Tiers 1-3
Cautions
- Published token rates increase for all tokens in a request once its prompt reaches xAI's 200,000-token long-context threshold
Best for
- Coding, agentic, and knowledge-work API evaluations with controlled long-context cost
Alternatives to Grok 4.6
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, same or higher score
Gemini 3.5 Flash-Lite
- 85% cheaper per 1M input tokens, $0.30 vs $2
- 1 points higher on Arena Text, 1455 vs 1454
- 1.05M context window vs 500K
- From Google
Claude Sonnet 5
- Same price per 1M input tokens, $2
- 7 points higher on Arena Text, 1461 vs 1454
- 1M context window vs 500K
- From Anthropic
Claude Sonnet 5.5
- Same price per 1M input tokens, $2
- 22 points higher on Arena Text, 1476 vs 1454
- 1M context window vs 500K
- From Anthropic
GPT-4.1
- Same price per 1M input tokens, $2
- 39 points lower on Arena Text, 1415 vs 1454
- 1.05M context window vs 500K
- From OpenAI
Compare Grok 4.6 with
Articles about Grok 4.6
- Grok 4.7: Same Price as Grok 4.6, but Check Cost per TaskSeptember 22, 2026
- Grok 4.6 and Persistent VM AgentsAugust 13, 2026
Other Grok 4 models
Grok 4.6 FAQ
How much does Grok 4.6 cost?
Grok 4.6 costs $2 per 1M input tokens and $6 per 1M output tokens at the standard tier. It is the #12 most expensive of 37 current text models priced per 1M input tokens. Source: SpaceXAI, verified August 14, 2026.
What is the context window of Grok 4.6?
Grok 4.6 accepts up to 500,000 tokens of context. That ranks #37 of 44 current text models by context length.
How does Grok 4.6 score on independent benchmarks?
Grok 4.6 scores 1454 Elo on Arena Text, #28 of 39 current models (Arena, measured October 8, 2026), 94% on GPQA Diamond, #9 of 37 current models (Epoch AI, measured October 12, 2026) and 66% on FrontierMath Tiers 1-3 (v2), #23 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not xAI's own launch figures.
Is Grok 4.6 open source or API only?
Grok 4.6 is available through xAI's API only; its weights are not published.
What are the best alternatives to Grok 4.6?
The closest current alternatives by price and measured performance are Gemini 3.5 Flash-Lite (85% cheaper per 1M input tokens, $0.30 vs $2), Claude Sonnet 5 (same price per 1M input tokens, $2), Claude Sonnet 5.5 (same price per 1M input tokens, $2) and GPT-4.1 (same price per 1M input tokens, $2).
Sources
- Introducing Grok 4.6 · SpaceXAI · official · verified August 14, 2026
- Grok 4.6 model · SpaceXAI · official · verified August 14, 2026
- SpaceXAI model pricing · SpaceXAI · official · verified August 14, 2026
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Grok 4.6 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/grok-4-6
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Grok 4.6 fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls