Grok 4.3: 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 | Healthy | 100%◆ (best) | 99.87% | 99.78% | 99.53%◆ (best) | 1.41s | 7.24s | 78 tps | 1.0M | $1.25 / $2.50◆ (best) |
xAIxai/zdr | Healthy | 100%◆ (best) | 99.91% | 99.85%◆ (best) | 99.51% | 1.32s | 3.54s | 81 tps | 1.0M | $1.25 / $2.50◆ (best) |
xAIxai/priority | No data | — | 99.58% | 97.98% | 96.42% | 616ms | 1.81s◆ (best) | 83 tps◆ (best) | 1.0M | $2.50 / $5.00 |
xAIxai/zdr/priority | No data | — | 99.91% | 98.48% | 96.44% | 549ms◆ (best) | 1.82s | 78 tps | 1.0M | $2.50 / $5.00 |
- xAI100%◆ (best)Healthy24h 99.87%
- 7d
- 99.78%
- 30d
- 99.53%◆ (best)
- p50
- 1.41s
- p99
- 7.24s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai - xAI100%◆ (best)Healthy24h 99.91%
- 7d
- 99.85%◆ (best)
- 30d
- 99.51%
- p50
- 1.32s
- p99
- 3.54s
- Throughput
- 81 tps
- Context
- 1.0M
- $/Mtok
- $1.25 / $2.50◆ (best)
xai/zdr - xAI—No data24h 99.58%
- 7d
- 97.98%
- 30d
- 96.42%
- p50
- 616ms
- p99
- 1.81s◆ (best)
- Throughput
- 83 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.50 / $5.00
xai/priority - xAI—No data24h 99.91%
- 7d
- 98.48%
- 30d
- 96.44%
- p50
- 549ms◆ (best)
- p99
- 1.82s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $2.50 / $5.00
xai/zdr/priority
Measured 3m 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.
Throughput
Median tokens per second.