Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instructInputOutput
Compare its 14 providersIncident RSSCompare with Llama 3.2 3B Instruct, Llama 3.2 1B Instruct, Llama 3.1 8B Instruct
CompareLlama 3.3 70B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.57% | 99.51% | 99.57% | 1.22s | 5.37s | 31 tps | 131K | $0.200 / $0.520 | |
| Healthy | 100% | 99.18% | 98.81% | 97.94% | 443ms | 4.13s | 59 tps | 24K | $0.293 / $2.25 | |
| Healthy | 100% | 99.81% | 99.70% | 99.84% | 405ms | 1.83s | 76 tps | 128K | $0.710 / $0.710 | |
| Degraded | 100% | 93.73% | 93.58% | 97.47% | 1.09s | 5.69s | 29 tps | 12K | $0.135 / $0.400 | |
SambaNovasambanova-turbo | Healthy | 100% | 99.26% | 99.13% | 98.85% | 771ms | 3.40s | 113 tps | 131K | $0.450 / $0.900 |
| Healthy | 99.94% | 99.04% | 98.61% | 99.34% | 603ms | 5.84s | 49 tps | 131K | $0.220 / $0.500 | |
Groqgroq | Healthy | 99.92% | 99.81% | 99.80% | 99.77% | 371ms | 1.05s | 252 tps | 131K | $0.590 / $0.790 |
| Healthy | 99.90% | 99.27% | 96.57% | 98.04% | 517ms | 4.86s | 19 tps | 131K | $0.100 / $0.320 | |
| No data | — | — | — | 99.87% | — | — | — | 131K | $0.250 / $0.750 | |
Googlegoogle-vertex | No data | — | — | — | 99.16% | — | — | — | 128K | $0.720 / $0.720 |
Googlegoogle-vertex/us-central1 | No data | — | — | — | 99.96% | — | — | — | 128K | $0.720 / $0.720 |
| No data | — | — | — | 56.08% | — | — | — | 131K | $0.130 / $0.400 | |
PrimeIntellectprimeintellect | No data | — | 95.52% | — | — | 655ms | 1.41s | 36 tps | 131K | $1.04 / $2.25 |
Togethertogether | No data | — | 99.02% | 98.38% | 97.98% | 650ms | 1.34s | 42 tps | 131K | $1.04 / $1.04 |
- AkashML100%Healthy24h 99.57%
- 7d
- 99.51%
- 30d
- 99.57%
- p50
- 1.22s
- p99
- 5.37s
- Throughput
- 31 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.520
akashml/fp8fp8 - Cloudflare100%Healthy24h 99.18%
- 7d
- 98.81%
- 30d
- 97.94%
- p50
- 443ms
- p99
- 4.13s
- Throughput
- 59 tps
- Context
- 24K
- $/Mtok
- $0.293 / $2.25
cloudflare/fp8fp8 - CoreWeave100%Healthy24h 99.81%
- 7d
- 99.70%
- 30d
- 99.84%
- p50
- 405ms
- p99
- 1.83s
- Throughput
- 76 tps
- Context
- 128K
- $/Mtok
- $0.710 / $0.710
coreweave/fp16fp16 - Novita100%Degraded24h 93.73%
- 7d
- 93.58%
- 30d
- 97.47%
- p50
- 1.09s
- p99
- 5.69s
- Throughput
- 29 tps
- Context
- 12K
- $/Mtok
- $0.135 / $0.400
novita/bf16bf16 - SambaNova100%Healthy24h 99.26%
- 7d
- 99.13%
- 30d
- 98.85%
- p50
- 771ms
- p99
- 3.40s
- Throughput
- 113 tps
- Context
- 131K
- $/Mtok
- $0.450 / $0.900
sambanova-turbo - Parasail99.94%Healthy24h 99.04%
- 7d
- 98.61%
- 30d
- 99.34%
- p50
- 603ms
- p99
- 5.84s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8 - Groq99.92%Healthy24h 99.81%
- 7d
- 99.80%
- 30d
- 99.77%
- p50
- 371ms
- p99
- 1.05s
- Throughput
- 252 tps
- Context
- 131K
- $/Mtok
- $0.590 / $0.790
groq - DeepInfra99.90%Healthy24h 99.27%
- 7d
- 96.57%
- 30d
- 98.04%
- p50
- 517ms
- p99
- 4.86s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - No data24h —
- 7d
- —
- 30d
- 99.87%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.250 / $0.750
crusoe/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 99.16%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex - No data24h —
- 7d
- —
- 30d
- 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex/us-central1 - No data24h —
- 7d
- —
- 30d
- 56.08%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8 - No data24h 95.52%
- 7d
- —
- 30d
- —
- p50
- 655ms
- p99
- 1.41s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $1.04 / $2.25
primeintellect - No data24h 99.02%
- 7d
- 98.38%
- 30d
- 97.98%
- p50
- 650ms
- p99
- 1.34s
- Throughput
- 42 tps
- Context
- 131K
- $/Mtok
- $1.04 / $1.04
together
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 14 endpoints · 47 days with data, 104 endpoint-days below 90%.
Price changes
- Llama 3.3 70B InstructAkashMLakashml/fp8$0.130 → $0.200 / $0.400 → $0.520cache read — → $0.1002026-08-19 09:50 UTC