Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) vs Grok 4.3
Both have similar output pricing, while Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) offers a larger context window. Choose Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) or Grok 4.3 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) | Grok 4.3 |
|---|---|---|
| Provider | LLM Gateway | SpaceXAI |
| Input / 1M tokens | $1.25 | $1.25 |
| Output / 1M tokens | $2.50 | $2.50 |
| Context window | 2M | 1M |
| Parameters | — | — |
| Open weights | No | — |
| Released | Mar 2026 | — |
| LiveBench score | — | 67.4 |
| GPQA Diamond score | — | 88.8 |
| LMArena (Chatbot Arena) Elo score | — | 1397 |
| LMArena WebDev Elo score | — | 1357 |
| LMArena Vision Elo score | — | 1229 |
FAQ
Is Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) or Grok 4.3 cheaper?
Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) and Grok 4.3 have comparable output pricing.
Which has the larger context window, Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) or Grok 4.3?
Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible)) has the larger context window (2M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.