Grok Build 0.1: 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 99.99%
- 7d
- 99.83%
- 30d
- 99.92%
- p50
- 697ms
- p99
- 3.80s
- Throughput
- 103 tps
- Context
- 256K
- $/Mtok
- $1.00 / $2.00◆ (best)
xai - xAI—No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 256K
- $/Mtok
- $2.00 / $4.00
xai/priority - xAI—No data24h 99.84%
- 7d
- 99.64%
- 30d
- 99.85%
- p50
- 667ms◆ (best)
- p99
- 1.40s◆ (best)
- Throughput
- 115 tps◆ (best)
- Context
- 256K
- $/Mtok
- $1.00 / $2.00◆ (best)
xai/zdr - xAI—No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 256K
- $/Mtok
- $2.00 / $4.00
xai/zdr/priority
Measured 2m 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.