Grok model for agentic tool use, reasoning, coding, and live assistance
Grok 4.20 by xai is offered by 5 providers on this page. Its reference price is $2.00 per 1M input tokens and $6.00 per 1M output tokens. The lowest paid channel is OpenRouter at $1.25 / $2.50 per 1M, about 1.6× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 25.7 on the Intelligence Index. Against its lowest blended price of $1.56 per 1M, that is roughly 16 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 113 tokens per second, with 19.93s to the first token.
The context window is 2,000,000 tokens at the reference host, but hosts report different limits, from 1,000,000 to 2,000,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-09-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OpenRouter | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 2,000,000 | 1,800,000 | |
| Merge Gateway xai/grok-4.20-0309-reasoning | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 ⚠ | 1,000,000 | |
| Kilo Gateway | Gateway | $1.25 | $2.50 | $0.20 | — | 2,000,000 | 1,800,000 | |
| Venice AI grok-4-20 | Gateway | $1.42 tiered >200K: $2.83 | $2.83 | $0.23 | — | 2,000,000 | 128,000 | |
| NanoGPT | Gateway | $2.00 | $6.00 | $1.00 | — | 2,000,000 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
2 / 5 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.