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% | 99.81% | 99.69% | 99.84% | 427ms | 1.59s | 77 tps | 128K | $0.710 / $0.710 | |
| Healthy | 100% | 92.33% | 93.71% | 97.48% | 846ms | 2.21s | 40 tps | 12K | $0.135 / $0.400 | |
SambaNovasambanova-turbo | Healthy | 100% | 99.18% | 99.17% | 98.86% | 734ms | 4.01s | 107 tps | 131K | $0.450 / $0.900 |
Togethertogether | Healthy | 100% | 98.86% | 98.19% | 97.97% | 600ms | 3.65s | 44 tps | 131K | $1.04 / $1.04 |
Groqgroq | Healthy | 99.87% | 99.82% | 99.79% | 99.78% | 384ms | 1.06s | 248 tps | 131K | $0.590 / $0.790 |
| Healthy | 99.71% | 99.18% | 96.41% | 98.03% | 399ms | 2.38s | 22 tps | 131K | $0.100 / $0.320 | |
| Healthy | 99.53% | 99.17% | 98.62% | 99.35% | 631ms | 5.84s | 46 tps | 131K | $0.220 / $0.500 | |
| Healthy | 99.02% | 99.23% | 98.81% | 97.93% | 474ms | 5.18s | 50 tps | 24K | $0.293 / $2.25 | |
| Healthy | 98.44% | 99.54% | 99.52% | 99.56% | 1.14s | 6.72s | 37 tps | 131K | $0.200 / $0.520 | |
| No data | — | — | — | 99.87% | — | — | — | 131K | $0.250 / $0.750 | |
Googlegoogle-vertex | No data | — | — | — | 99.17% | — | — | — | 128K | $0.720 / $0.720 |
Googlegoogle-vertex/us-central1 | No data | — | — | — | 99.96% | 1.04s | 2.00s | 92 tps | 128K | $0.720 / $0.720 |
| No data | — | — | — | 55.29% | — | — | — | 131K | $0.130 / $0.400 |
- CoreWeave100%Healthy24h 99.81%
- 7d
- 99.69%
- 30d
- 99.84%
- p50
- 427ms
- p99
- 1.59s
- Throughput
- 77 tps
- Context
- 128K
- $/Mtok
- $0.710 / $0.710
coreweave/fp16fp16 - Novita100%Healthy24h 92.33%
- 7d
- 93.71%
- 30d
- 97.48%
- p50
- 846ms
- p99
- 2.21s
- Throughput
- 40 tps
- Context
- 12K
- $/Mtok
- $0.135 / $0.400
novita/bf16bf16 - SambaNova100%Healthy24h 99.18%
- 7d
- 99.17%
- 30d
- 98.86%
- p50
- 734ms
- p99
- 4.01s
- Throughput
- 107 tps
- Context
- 131K
- $/Mtok
- $0.450 / $0.900
sambanova-turbo - Together100%Healthy24h 98.86%
- 7d
- 98.19%
- 30d
- 97.97%
- p50
- 600ms
- p99
- 3.65s
- Throughput
- 44 tps
- Context
- 131K
- $/Mtok
- $1.04 / $1.04
together - Groq99.87%Healthy24h 99.82%
- 7d
- 99.79%
- 30d
- 99.78%
- p50
- 384ms
- p99
- 1.06s
- Throughput
- 248 tps
- Context
- 131K
- $/Mtok
- $0.590 / $0.790
groq - DeepInfra99.71%Healthy24h 99.18%
- 7d
- 96.41%
- 30d
- 98.03%
- p50
- 399ms
- p99
- 2.38s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.320
deepinfra/turbofp8 - Parasail99.53%Healthy24h 99.17%
- 7d
- 98.62%
- 30d
- 99.35%
- p50
- 631ms
- p99
- 5.84s
- Throughput
- 46 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8 - Cloudflare99.02%Healthy24h 99.23%
- 7d
- 98.81%
- 30d
- 97.93%
- p50
- 474ms
- p99
- 5.18s
- Throughput
- 50 tps
- Context
- 24K
- $/Mtok
- $0.293 / $2.25
cloudflare/fp8fp8 - AkashML98.44%Healthy24h 99.54%
- 7d
- 99.52%
- 30d
- 99.56%
- p50
- 1.14s
- p99
- 6.72s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.520
akashml/fp8fp8 - No data24h —
- 7d
- —
- 30d
- 99.87%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.250 / $0.750
crusoe/bf16bf16 - No data24h —
- 7d
- —
- 30d
- 99.17%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex - No data24h —
- 7d
- —
- 30d
- 99.96%
- p50
- 1.04s
- p99
- 2.00s
- Throughput
- 92 tps
- Context
- 128K
- $/Mtok
- $0.720 / $0.720
google-vertex/us-central1 - No data24h —
- 7d
- —
- 30d
- 55.29%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8
Measured 3m 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, 107 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