Grok 4.20 benchmarks, pricing and specs
Grok 4.20 is a xAI model released on March 10, 2026 that takes text and image input and produces text. It costs $1.25 per 1M input tokens and $2.50 per 1M output tokens and accepts up to 1,000,000 tokens of context. It scores 1472 Elo on Arena Text, #22 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $1.25
- Per 1M output tokens
- $2.50
- Context window
- 1M
- Arena Text
- 1472 Elo · #22/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- xAI
- Model family
- Grok 4
- Release date
- March 10, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 1,000,000 tokens
- Max output
- Not reported
- Input
- text, image
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning
Grok 4.20 pricing
It is the #12 cheapest 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 | 1472 Elo | #22 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 89.3% | #28 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 44.9% | #31 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| SimpleQA Verified | 30.2% | #30 of 34 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Grok 4.20 supports text and image input and is available in reasoning, non-reasoning, and multi-agent API variants
Cautions
- The published base rates double when requests reach the provider's 200,000-token long-context threshold
Best for
- Comparing single-agent and multi-agent reasoning on long-context workloads
Alternatives to Grok 4.20
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
DeepSeek-V4.1-Flash
- 76% cheaper per 1M input tokens, $0.30 vs $1.25
- 3 points higher on Arena Text, 1475 vs 1472
- From DeepSeek
Muse Spark 1.3
- Same price per 1M input tokens, $1.25
- 22 points higher on Arena Text, 1494 vs 1472
- From Meta
Mistral Large 4
- 9% more per 1M input tokens, $1.36 vs $1.25
- 43 points lower on Arena Text, 1429 vs 1472
- From Mistral AI
Gemini 3.6 Flash
- 20% more per 1M input tokens, $1.50 vs $1.25
- 10 points higher on Arena Text, 1482 vs 1472
- From Google
Compare Grok 4.20 with
Other Grok 4 models
Grok 4.20 FAQ
How much does Grok 4.20 cost?
Grok 4.20 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens at the standard tier. It is the #12 cheapest of 37 current text models priced per 1M input tokens. Source: SpaceXAI, verified August 14, 2026.
What is the context window of Grok 4.20?
Grok 4.20 accepts up to 1,000,000 tokens of context. That ranks #24 of 44 current text models by context length.
How does Grok 4.20 score on independent benchmarks?
Grok 4.20 scores 1472 Elo on Arena Text, #22 of 39 current models (Arena, measured October 8, 2026), 89.3% on GPQA Diamond, #28 of 37 current models (Epoch AI, measured October 12, 2026) and 44.9% on FrontierMath Tiers 1-3 (v2), #31 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not xAI's own launch figures.
Is Grok 4.20 open source or API only?
Grok 4.20 is available through xAI's API only; its weights are not published.
What are the best alternatives to Grok 4.20?
The closest current alternatives by price and measured performance are DeepSeek-V4.1-Flash (76% cheaper per 1M input tokens, $0.30 vs $1.25), Muse Spark 1.3 (same price per 1M input tokens, $1.25), Mistral Large 4 (9% more per 1M input tokens, $1.36 vs $1.25) and Gemini 3.6 Flash (20% more per 1M input tokens, $1.50 vs $1.25).
Sources
- SpaceXAI API release notes · SpaceXAI · official · verified August 7, 2026
- Grok 4.20 System Card · SpaceXAI · official · verified August 7, 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 4.20 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/grok-4-20
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Grok 4.20 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