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% | 99.56% | 99.51% | 99.57% | 1.17s | 7.02s | 38 tps | 131K | $0.200 / $0.520 | |
| Healthy | 100% | 99.19% | 98.81% | 97.93% | 476ms | 4.19s | 55 tps | 24K | $0.293 / $2.25 | |
| Healthy | 100% | 99.81% | 99.70% | 99.84% | 433ms | 2.46s | 71 tps | 128K | $0.710 / $0.710 | |
| Healthy | 100% | 93.80% | 93.64% | 97.48% | 1.21s | 3.39s | 28 tps | 12K | $0.135 / $0.400 | |
Groqgroq | Healthy | 99.90% | 99.81% | 99.80% | 99.77% | 376ms | 1.05s | 241 tps | 131K | $0.590 / $0.790 |
| Healthy | 98.96% | 99.06% | 98.61% | 99.35% | 584ms | 6.30s | 51 tps | 131K | $0.220 / $0.500 | |
SambaNovasambanova-turbo | Degraded | 93.26% | 99.27% | 99.15% | 98.86% | 785ms | 4.00s | 112 tps | 131K | $0.450 / $0.900 |
| Degraded | 90.67% | 99.24% | 96.45% | 98.04% | 637ms | 5.47s | 15 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 | — | — | — | 55.97% | — | — | — | 131K | $0.130 / $0.400 | |
PrimeIntellectprimeintellect | No data | — | — | — | — | — | — | — | 131K | $1.04 / $2.25 |
Togethertogether | No data | — | 98.98% | 98.37% | 97.98% | 783ms | 3.82s | 40 tps | 131K | $1.04 / $1.04 |
- AkashML100%Healthy24h 99.56%
- 7d
- 99.51%
- 30d
- 99.57%
- p50
- 1.17s
- p99
- 7.02s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.520
akashml/fp8fp8 - Cloudflare100%Healthy24h 99.19%
- 7d
- 98.81%
- 30d
- 97.93%
- p50
- 476ms
- p99
- 4.19s
- Throughput
- 55 tps
- Context
- 24K
- $/Mtok
- $0.293 / $2.25
cloudflare/fp8fp8 - CoreWeave100%Healthy24h 99.81%
- 7d
- 99.70%
- 30d
- 99.84%
- p50
- 433ms
- p99
- 2.46s
- Throughput
- 71 tps
- Context
- 128K
- $/Mtok
- $0.710 / $0.710
coreweave/fp16fp16 - Novita100%Healthy24h 93.80%
- 7d
- 93.64%
- 30d
- 97.48%
- p50
- 1.21s
- p99
- 3.39s
- Throughput
- 28 tps
- Context
- 12K
- $/Mtok
- $0.135 / $0.400
novita/bf16bf16 - Groq99.90%Healthy24h 99.81%
- 7d
- 99.80%
- 30d
- 99.77%
- p50
- 376ms
- p99
- 1.05s
- Throughput
- 241 tps
- Context
- 131K
- $/Mtok
- $0.590 / $0.790
groq - Parasail98.96%Healthy24h 99.06%
- 7d
- 98.61%
- 30d
- 99.35%
- p50
- 584ms
- p99
- 6.30s
- Throughput
- 51 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8 - SambaNova93.26%Degraded24h 99.27%
- 7d
- 99.15%
- 30d
- 98.86%
- p50
- 785ms
- p99
- 4.00s
- Throughput
- 112 tps
- Context
- 131K
- $/Mtok
- $0.450 / $0.900
sambanova-turbo - DeepInfra90.67%Degraded24h 99.24%
- 7d
- 96.45%
- 30d
- 98.04%
- p50
- 637ms
- p99
- 5.47s
- Throughput
- 15 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
- 55.97%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $1.04 / $2.25
primeintellect - No data24h 98.98%
- 7d
- 98.37%
- 30d
- 97.98%
- p50
- 783ms
- p99
- 3.82s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $1.04 / $1.04
together
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint has 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, 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, 103 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