Granite 4.2 8B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- CoreWeave100%Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 96.77%
- p50
- 314ms◆ (best)
- p99
- 979ms◆ (best)
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.150
coreweave/bf16bf16 - No data24h 99.98%
- 7d
- 99.98%◆ (best)
- 30d
- 99.99%◆ (best)
- p50
- 577ms
- p99
- 1.41s
- Throughput
- 111 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.060 / $0.250◆ (best)
deepinfra/bf16bf16
Measured 5m 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.