Llama 3.1 Euryale 70B v2.2: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- DeepInfra100%Healthy24h 99.93%
- 7d
- 99.73%
- 30d
- 99.26%◆ (best)
- p50
- 187ms◆ (best)
- p99
- 3.02s
- Throughput
- 40 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.850 / $0.850◆ (best)
deepinfra/fp8fp8 - No data24h 99.91%
- 7d
- 100%◆ (best)
- 30d
- 95.70%
- p50
- 497ms
- p99
- 2.38s◆ (best)
- Throughput
- 35 tps
- Context
- 8K
- $/Mtok
- $1.45 / $1.45
novita/fp8fp8
Measured 4m 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.