Grok 4.3 (Azure) vs Grok 4.20 (Non-Reasoning)
Both have similar output pricing, while Grok 4.20 (Non-Reasoning) offers a larger context window. Choose Grok 4.3 (Azure) or Grok 4.20 (Non-Reasoning) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Grok 4.3 (Azure) | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | LLM Gateway | xAI |
| Input / 1M tokens | $1.25 | $1.25 |
| Output / 1M tokens | $2.50 | $2.50 |
| Context window | 200K | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Apr 2026 | Mar 2026 |
| LiveBench score | — | 37.9 |
FAQ
Is Grok 4.3 (Azure) or Grok 4.20 (Non-Reasoning) cheaper?
Grok 4.3 (Azure) and Grok 4.20 (Non-Reasoning) have comparable output pricing.
Which has the larger context window, Grok 4.3 (Azure) or Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.