Grok 4.20: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- xAI—No data24h —
- 7d
- 99.58%
- 30d
- 99.66%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai - xAI—No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/priority - xAI—No data24h —
- 7d
- 99.72%
- 30d
- 99.74%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai/zdr - xAI—No data24h —
- 7d
- 100%
- 30d
- 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/zdr/priority
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.