AI model comparison
Grok 4.3 vs Grok 4.20
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Tie
Same price for a typical chat
Higher intelligence score
Grok 4.20
25.7 vs 24.9 on Artificial Analysis
Larger context window
Grok 4.20
2M vs 1M tokens
Newer release
Grok 4.3
Released April 30, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
Grok 4.3 vs Grok 4.20 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $1.25 | $1.25 |
| Output tokensPer 1M tokens | $2.50 | $2.50 |
| Cached input (read)Per 1M tokens | $0.20 | $0.20 |
| Cache writePer 1M tokens | Not available | Not available |
| Long-context pricingPer 1M tokens, for very long prompts | $2.50 in / $5 out above 200K | $2.50 in / $5 out above 200K |
| Web searchPer request | $0.005 | $0.005 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Coding task
30K in, 4K out
Long document summary
150K in, 2K out
Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | ||
|---|---|---|
| Context window | 1M tokens | 2M tokens |
| Max output | 900K tokens | 1.80M tokens |
| Input types | File, Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, None | Not available |
| Default reasoning effort | Low | Not available |
| Release date | April 30, 2026 | March 31, 2026 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Not supported | Not supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
- Grok 4.3 vs Grok Build 0.1
- Grok 4.3 vs Kimi K2.6
- Grok 4.3 vs DeepSeek V4 Flash 0423
- Grok 4.3 vs Gemini 3 Flash Preview
- Grok 4.3 vs GLM 5.1
- Grok 4.3 vs Kimi K2.7 Code
- Grok 4.3 vs Qwen3.7 Plus
- Grok 4.3 vs Inkling
- Grok 4.3 vs GPT-5.4 Mini
- Grok 4.3 vs Kimi K2.5
- Grok 4.3 vs Nemotron 3 Ultra
- Grok 4.3 vs Qwen3.5-27B
- Grok 4.3 vs Gemini 3.5 Flash Lite
- Grok 4.20 vs Grok Build 0.1
- Grok 4.20 vs Kimi K2.6
- Grok 4.20 vs Qwen3.6 Plus
- Grok 4.20 vs GLM 5 Turbo
- Grok 4.20 vs Gemini 3 Flash Preview
- Grok 4.20 vs GLM 5.1
- Grok 4.20 vs Kimi K2.7 Code
- Grok 4.20 vs Inkling Small
- Grok 4.20 vs Qwen3.7 Plus
- Grok 4.20 vs Inkling
- Grok 4.20 vs DeepSeek V4 Flash 0423
- Grok 4.20 vs Gemini 3.5 Flash Lite
Our take
Grok 4.20 scores higher on the Artificial Analysis Intelligence Index (25.7 vs 24.9). Grok 4.20 has the larger context window (2M vs 1M tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Grok 4.3 or Grok 4.20 cheaper?
Grok 4.3 and Grok 4.20 cost the same for a typical chat (2K input tokens and 500 output tokens). Grok 4.3 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens, and Grok 4.20 costs $1.25 per 1M input tokens and $2.50 per 1M output tokens.
Which has a bigger context window, Grok 4.3 or Grok 4.20?
Grok 4.20 supports up to 2M tokens of context, compared with 1M for Grok 4.3.
Is Grok 4.3 smarter than Grok 4.20?
On the Artificial Analysis Intelligence Index, Grok 4.3 scores 24.9 and Grok 4.20 scores 25.7, putting Grok 4.20 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Grok 4.3 and Grok 4.20 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Grok 4.3 and Grok 4.20 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Grok 4.3 and Grok 4.20 at the same time. Compare the answers side by side and keep the best one.