Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
Compare with Llama 3.1 8B Instruct, Llama 4 Maverick, Llama 4 Scout
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AkashMLakashml/fp8fp8 | Healthy | 100% | 97.87% | 846ms | 5.51s | 19 tps | 131K | $0.200 / $0.520 |
CoreWeavecoreweave/fp16fp16 | Healthy | 100% | 99.15% | 206ms | 1.09s | 34 tps | 128K | $0.710 / $0.710 |
Crusoecrusoe/bf16bf16 | Healthy | 100% | 98.73% | 442ms | 4.65s | 34 tps | 131K | $0.250 / $0.750 |
Googlegoogle-vertex/us-central1 | Healthy | 100% | 99.98% | 319ms | 2.07s | 52 tps | 128K | $0.720 / $0.720 |
Groqgroq | Healthy | 100% | 99.89% | 200ms | 627ms | 18 tps | 131K | $0.590 / $0.790 |
Parasailparasail/fp8fp8 | Healthy | 100% | 97.37% | 716ms | 6.59s | 32 tps | 131K | $0.220 / $0.500 |
Novitanovita/bf16bf16 | Healthy | 99.03% | 95.46% | 884ms | 3.84s | 27 tps | 12K | $0.135 / $0.400 |
Cloudflarecloudflare/fp8fp8 | Degraded | 98.15% | 90.54% | 1.03s | 7.21s | 22 tps | 24K | $0.293 / $2.25 |
DeepInfradeepinfra/turbofp8 | Healthy | 97.80% | 96.91% | 516ms | 5.90s | 12 tps | 131K | $0.100 / $0.320 |
SambaNovasambanova-turbo | Degraded | 93.86% | 97.96% | 714ms | 5.04s | 83 tps | 131K | $0.450 / $0.900 |
Googlegoogle-vertex | No data | — | 97.25% | 317ms | 1.90s | 36 tps | 128K | $0.720 / $0.720 |
Nebiusnebius/fp8fp8 | Down | — | 44.51% | 1.07s | 17.6s | 14 tps | 131K | $0.130 / $0.400 |
Togethertogether | No data | — | 98.35% | 1.07s | 4.28s | 14 tps | 131K | $1.04 / $1.04 |
- AkashML100%Healthy24h 97.87%
- p50
- 846ms
- p99
- 5.51s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.520
akashml/fp8fp8 - CoreWeave100%Healthy24h 99.15%
- p50
- 206ms
- p99
- 1.09s
- Throughput
- 34 tps
- Context
- 128K
- $/Mtok
- $0.710 / $0.710
coreweave/fp16fp16 - Crusoe100%Healthy24h 98.73%
- p50
- 442ms
- p99
- 4.65s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.250 / $0.750
crusoe/bf16bf16 - Google100%Healthy24h 99.98%
- p50
- 319ms
- p99
- 2.07s
- Throughput
- 52 tps
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex/us-central1 - Groq100%Healthy24h 99.89%
- p50
- 200ms
- p99
- 627ms
- Throughput
- 18 tps
- Context
- 131K
- $/Mtok
- $0.590 / $0.790
groq - Parasail100%Healthy24h 97.37%
- p50
- 716ms
- p99
- 6.59s
- Throughput
- 32 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8 - Novita99.03%Healthy24h 95.46%
- p50
- 884ms
- p99
- 3.84s
- Throughput
- 27 tps
- Context
- 12K
- $/Mtok
- $0.135 / $0.400
novita/bf16bf16 - Cloudflare98.15%Degraded24h 90.54%
- p50
- 1.03s
- p99
- 7.21s
- Throughput
- 22 tps
- Context
- 24K
- $/Mtok
- $0.293 / $2.25
cloudflare/fp8fp8 - DeepInfra97.80%Healthy24h 96.91%
- p50
- 516ms
- p99
- 5.90s
- Throughput
- 12 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - SambaNova93.86%Degraded24h 97.96%
- p50
- 714ms
- p99
- 5.04s
- Throughput
- 83 tps
- Context
- 131K
- $/Mtok
- $0.450 / $0.900
sambanova-turbo - Google—No data24h 97.25%
- p50
- 317ms
- p99
- 1.90s
- Throughput
- 36 tps
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex - Nebius—Down24h 44.51%
- p50
- 1.07s
- p99
- 17.6s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8 - Together—No data24h 98.35%
- p50
- 1.07s
- p99
- 4.28s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $1.04 / $1.04
together
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.