Llama 3.1 8B Instruct: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.09% | 99.06% | 98.76% | 493ms | 20.8s | 17 tps | 32K | $0.152 / $0.287 | |
| Healthy | 100%◆ (best) | 99.99% | 100%◆ (best) | 99.97%◆ (best) | 199ms◆ (best) | 1.89s◆ (best) | 133 tps | 131K | $0.220 / $0.220 | |
| Healthy | 100%◆ (best) | 99.93% | 99.07% | 99.19% | 809ms | 2.69s | 36 tps | 131K | $0.020 / $0.040◆ (best) | |
| Healthy | 100%◆ (best) | 98.89% | 99.14% | 98.66% | 538ms | 3.53s | 100 tps | 16K | $0.020 / $0.050◆ (best) | |
Groqgroq | Healthy | 99.96% | 99.62% | 99.69% | 99.64% | 408ms | 4.76s | 223 tps◆ (best) | 131K | $0.050 / $0.080 |
- Cloudflare100%◆ (best)Healthy24h 99.09%
- 7d
- 99.06%
- 30d
- 98.76%
- p50
- 493ms
- p99
- 20.8s
- Throughput
- 17 tps
- Context
- 32K
- $/Mtok
- $0.152 / $0.287
cloudflare/fp8fp8 - CoreWeave100%◆ (best)Healthy24h 99.99%
- 7d
- 100%◆ (best)
- 30d
- 99.97%◆ (best)
- p50
- 199ms◆ (best)
- p99
- 1.89s◆ (best)
- Throughput
- 133 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.220
coreweave/bf16bf16 - DeepInfra100%◆ (best)Healthy24h 99.93%
- 7d
- 99.07%
- 30d
- 99.19%
- p50
- 809ms
- p99
- 2.69s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.040◆ (best)
deepinfra/fp8fp8 - Novita100%◆ (best)Healthy24h 98.89%
- 7d
- 99.14%
- 30d
- 98.66%
- p50
- 538ms
- p99
- 3.53s
- Throughput
- 100 tps
- Context
- 16K
- $/Mtok
- $0.020 / $0.050◆ (best)
novita/fp8fp8 - Groq99.96%Healthy24h 99.62%
- 7d
- 99.69%
- 30d
- 99.64%
- p50
- 408ms
- p99
- 4.76s
- Throughput
- 223 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.050 / $0.080
groq
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.