Grok 4.6
x-ai/grok-4.6InputOutput
Compare its 6 providersIncident RSSCompare with Grok 4.5, Grok 4.7, Grok 4.3
CompareGrok 4.6
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
xAIxai | Healthy | 100% | 99.48% | 99.54% | 99.56% | 2.62s | 19.1s | 61 tps | 500K | $2.00 / $6.00 |
xAIxai/zdr | Healthy | 100% | 99.39% | 99.70% | 99.72% | 2.45s | 17.6s | 60 tps | 500K | $2.00 / $6.00 |
Amazon Bedrockamazon-bedrock/us-west-2 | No data | — | 100% | 100% | 100% | 5.79s | 16.9s | 142 tps | 500K | $2.20 / $6.60 |
xAIxai/priority | No data | — | — | — | 99.88% | — | — | — | 500K | $4.00 / $12.00 |
xAIxai/zdr/priority | No data | — | 98.46% | 100% | 99.24% | 2.02s | 26.2s | 55 tps | 500K | $4.00 / $12.00 |
xAIxai/zdr/us | No data | — | 90.91% | 100% | 100% | 2.13s | 5.91s | 55 tps | 500K | $2.20 / $6.60 |
- xAI100%Healthy24h 99.48%
- 7d
- 99.54%
- 30d
- 99.56%
- p50
- 2.62s
- p99
- 19.1s
- Throughput
- 61 tps
- Context
- 500K
- $/Mtok
- $2.00 / $6.00
xai - xAI100%Healthy24h 99.39%
- 7d
- 99.70%
- 30d
- 99.72%
- p50
- 2.45s
- p99
- 17.6s
- Throughput
- 60 tps
- Context
- 500K
- $/Mtok
- $2.00 / $6.00
xai/zdr - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 5.79s
- p99
- 16.9s
- Throughput
- 142 tps
- Context
- 500K
- $/Mtok
- $2.20 / $6.60
amazon-bedrock/us-west-2 - xAI—No data24h —
- 7d
- —
- 30d
- 99.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 500K
- $/Mtok
- $4.00 / $12.00
xai/priority - xAI—No data24h 98.46%
- 7d
- 100%
- 30d
- 99.24%
- p50
- 2.02s
- p99
- 26.2s
- Throughput
- 55 tps
- Context
- 500K
- $/Mtok
- $4.00 / $12.00
xai/zdr/priority - xAI—No data24h 90.91%
- 7d
- 100%
- 30d
- 100%
- p50
- 2.13s
- p99
- 5.91s
- Throughput
- 55 tps
- Context
- 500K
- $/Mtok
- $2.20 / $6.60
xai/zdr/us
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 48 days with data, 12 endpoint-days below 90%.