Grok 4.20
x-ai/grok-4.20
Compare with Grok 4.20 Multi-Agent, Grok 4.3, Grok 4.5
CompareGrok 4.20
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
xAIxai | Healthy | 100% | 99.82% | 604ms | 10.4s | 71 tps | 2.0M | $1.25 / $2.50 |
xAIxai/priority | Healthy | 100% | 99.82% | — | — | — | 2.0M | $2.50 / $5.00 |
xAIxai/zdr | No data | — | 99.83% | 626ms | 2.32s | 81 tps | 2.0M | $1.25 / $2.50 |
xAIxai/zdr/priority | No data | — | 99.83% | — | — | — | 2.0M | $2.50 / $5.00 |
- xAI100%Healthy24h 99.82%
- p50
- 604ms
- p99
- 10.4s
- Throughput
- 71 tps
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50
xai - xAI100%Healthy24h 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/priority - xAI—No data24h 99.83%
- p50
- 626ms
- p99
- 2.32s
- Throughput
- 81 tps
- Context
- 2.0M
- $/Mtok
- $1.25 / $2.50
xai/zdr - xAI—No data24h 99.83%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 2.0M
- $/Mtok
- $2.50 / $5.00
xai/zdr/priority
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.