Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instructInputOutput
Compare its 13 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% | 99.56% | 99.51% | 99.57% | 971ms | 5.70s | 39 tps | 131K | $0.200 / $0.520 | |
| Healthy | 100% | 99.19% | 98.81% | 97.93% | 483ms | 4.94s | 45 tps | 24K | $0.293 / $2.25 | |
| Healthy | 100% | 99.81% | 99.70% | 99.84% | 460ms | 1.45s | 80 tps | 128K | $0.710 / $0.710 | |
Groqgroq | Healthy | 99.93% | 99.81% | 99.80% | 99.77% | 376ms | 1.12s | 249 tps | 131K | $0.590 / $0.790 |
| Healthy | 99.90% | 99.24% | 96.44% | 98.04% | 446ms | 4.36s | 26 tps | 131K | $0.100 / $0.320 | |
| Healthy | 99.71% | 99.08% | 98.61% | 99.35% | 579ms | 2.84s | 51 tps | 131K | $0.220 / $0.500 | |
| Degraded | 99.33% | 93.70% | 93.66% | 97.48% | 929ms | 4.78s | 26 tps | 12K | $0.135 / $0.400 | |
SambaNovasambanova-turbo | Healthy | 99.20% | 99.28% | 99.15% | 98.86% | 765ms | 4.83s | 104 tps | 131K | $0.450 / $0.900 |
| 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% | 1.77s | 1.77s | 112 tps | 128K | $0.720 / $0.720 |
| No data | — | — | — | 55.79% | — | — | — | 131K | $0.130 / $0.400 | |
Togethertogether | No data | — | 98.98% | 98.37% | 97.98% | 527ms | 1.79s | 43 tps | 131K | $1.04 / $1.04 |
- AkashML100%Healthy24h 99.56%
- 7d
- 99.51%
- 30d
- 99.57%
- p50
- 971ms
- p99
- 5.70s
- Throughput
- 39 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.520
akashml/fp8fp8 - Cloudflare100%Healthy24h 99.19%
- 7d
- 98.81%
- 30d
- 97.93%
- p50
- 483ms
- p99
- 4.94s
- Throughput
- 45 tps
- Context
- 24K
- $/Mtok
- $0.293 / $2.25
cloudflare/fp8fp8 - CoreWeave100%Healthy24h 99.81%
- 7d
- 99.70%
- 30d
- 99.84%
- p50
- 460ms
- p99
- 1.45s
- Throughput
- 80 tps
- Context
- 128K
- $/Mtok
- $0.710 / $0.710
coreweave/fp16fp16 - Groq99.93%Healthy24h 99.81%
- 7d
- 99.80%
- 30d
- 99.77%
- p50
- 376ms
- p99
- 1.12s
- Throughput
- 249 tps
- Context
- 131K
- $/Mtok
- $0.590 / $0.790
groq - DeepInfra99.90%Healthy24h 99.24%
- 7d
- 96.44%
- 30d
- 98.04%
- p50
- 446ms
- p99
- 4.36s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - Parasail99.71%Healthy24h 99.08%
- 7d
- 98.61%
- 30d
- 99.35%
- p50
- 579ms
- p99
- 2.84s
- Throughput
- 51 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8 - Novita99.33%Degraded24h 93.70%
- 7d
- 93.66%
- 30d
- 97.48%
- p50
- 929ms
- p99
- 4.78s
- Throughput
- 26 tps
- Context
- 12K
- $/Mtok
- $0.135 / $0.400
novita/bf16bf16 - SambaNova99.20%Healthy24h 99.28%
- 7d
- 99.15%
- 30d
- 98.86%
- p50
- 765ms
- p99
- 4.83s
- Throughput
- 104 tps
- Context
- 131K
- $/Mtok
- $0.450 / $0.900
sambanova-turbo - 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
- 1.77s
- p99
- 1.77s
- Throughput
- 112 tps
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex/us-central1 - No data24h —
- 7d
- —
- 30d
- 55.79%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8 - No data24h 98.98%
- 7d
- 98.37%
- 30d
- 97.98%
- p50
- 527ms
- p99
- 1.79s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $1.04 / $1.04
together
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints have no chartable data in this range.
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.
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 · 13 endpoints · 46 days with data, 108 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