Grok 4 20 Non Reasoning vs Grok 4.3
API pricing, context window and capabilities for Grok 4 20 Non Reasoning and Grok 4.3, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersGrok 4 20 Non Reasoning wins on context window. Grok 4.3 wins on intelligence. Benchmark data is unavailable for one or both models.
Price
Tied
Terminal-Bench
Not called
Intelligence
Grok 4.3
Context window
Grok 4 20 Non Reasoning
Key takeaways
who wins on what, from the published numbersGrok 4 20 Non Reasoning wins
- Larger context window (2M vs 1M)
- Higher max output (2M vs 1M)
Grok 4.3 wins
- More serving providers (5 vs 6)
Cheaper overall
Tied
Larger context
Grok 4 20 Non Reasoning
2M
More providers
Grok 4.3
6 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| Grok 4 20 Non Reasoning | Grok 4.3 | |
|---|---|---|
| Input $/1M | $1.25via xAI | $1.25via xAI |
| Output $/1M | $2.50via xAI | $2.50via xAI |
| Context window | 2M best | 1M |
| Max output | 2M best | 1M |
| Serving providers | 5 | 6 best |
| Date | Released Mar 9, 2026 | Released Apr 18, 2026 |
Benchmarks
Benchmark scores, side by side| Grok 4 20 Non Reasoning | Grok 4.3 | |
|---|---|---|
| Intelligence | 14.2 | 24.9 best |
| Terminal-Bench | Not available | 40% |
| GPQA Diamond | 78% | 90% best |
| Output speed | 94 t/s | 113 t/s best |
| Latency (TTFT) | 0.62s best | 27.23s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Grok 4 20 Non Reasoning
via Azure
$8.75
Grok 4.3
via OpenRouter
$8.75
Capabilities
feature support, side by side| Feature | Grok 4 20 Non Reasoning | Grok 4.3 |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | ✓ | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, Grok 4 20 Non Reasoning or Grok 4.3?
Grok 4 20 Non Reasoning and Grok 4.3 have the same cheapest published input and output rates.
What is the context window difference between Grok 4 20 Non Reasoning and Grok 4.3?
Grok 4 20 Non Reasoning has a 2M-token context window and Grok 4.3 has 1M tokens, so Grok 4 20 Non Reasoning can take a larger prompt.
How do Grok 4 20 Non Reasoning and Grok 4.3 compare on benchmarks?
On the tracked benchmarks, Grok 4.3 leads on intelligence.
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