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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
xAIxai/zdr | Healthy | 100%◆ (best) | 99.96% | 99.72% | 99.74% | 759ms | 8.32s | 76 tps | 2.0M | $1.25 / $2.50◆ (best) |
xAIxai | Healthy | 99.91% | 99.94% | 99.58% | 99.66% | 723ms | 6.88s | 81 tps◆ (best) | 2.0M | $1.25 / $2.50◆ (best) |
xAIxai/priority | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 2.0M | $2.50 / $5.00 |
xAIxai/zdr/priority | No data | — | 100% | 100% | 99.96% | 478ms◆ (best) | 688ms◆ (best) | 77 tps | 2.0M | $2.50 / $5.00 |
- xAI100%◆ (best)Healthy24h 99.96%
- 7d
- 99.72%
- 30d
- 99.74%
- p50
- 759ms
- p99
- 8.32s
- Throughput
- 76 tps
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai/zdr - xAI99.91%Healthy24h 99.94%
- 7d
- 99.58%
- 30d
- 99.66%
- p50
- 723ms
- p99
- 6.88s
- Throughput
- 81 tps◆ (best)
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai - xAI—No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/priority - xAI—No data24h 100%
- 7d
- 100%
- 30d
- 99.96%
- p50
- 478ms◆ (best)
- p99
- 688ms◆ (best)
- Throughput
- 77 tps
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/zdr/priority
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.