Grok 4.20

ChatInput: TextInput: ImageInput: FileReleased Mar 31, 2026

Built by SpaceXAI · United States · x.ai

2M context

How to use

model: "xai/grok-4.20"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "xai/grok-4.20",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

Max output

—

Input $/1M

$1.25

Output $/1M

$2.50

Features

Image inputTool callingJSON

Serving providers

SpaceXAI

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

152.6

Terminal-BenchAgentic terminal tasks

57.3%

ARC-AGI-2Abstract reasoning

65.1%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…