Llama 4 Maverick
meta-llama/llama-4-maverick
Compare with Llama 4 Scout, Llama Guard 4 12B, Llama 3.3 70B Instruct
CompareLlama 4 Maverick
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/basefp8 | Healthy | 100% | 99.08% | 311ms | 1.78s | 38 tps | 1.0M | $0.200 / $0.800 |
Googlegoogle-vertex/us-east5 | Healthy | 100% | 99.88% | 789ms | 2.00s | 94 tps | 524K | $0.350 / $1.15 |
Novitanovita/fp8fp8 | Healthy | 100% | 98.07% | 516ms | 1.27s | 34 tps | 1.0M | $0.270 / $0.850 |
Parasailparasail/fp8fp8 | Healthy | 100% | 99.95% | 521ms | 2.63s | 41 tps | 524K | $0.350 / $1.00 |
DigitalOceandigitalocean | Healthy | 99.89% | 98.75% | 567ms | 4.17s | 8.0 tps | 128K | $0.200 / $0.696 |
- DeepInfra100%Healthy24h 99.08%
- p50
- 311ms
- p99
- 1.78s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.800
deepinfra/basefp8 - Google100%Healthy24h 99.88%
- p50
- 789ms
- p99
- 2.00s
- Throughput
- 94 tps
- Context
- 524K
- $/Mtok
- $0.350 / $1.15
google-vertex/us-east5 - Novita100%Healthy24h 98.07%
- p50
- 516ms
- p99
- 1.27s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.270 / $0.850
novita/fp8fp8 - Parasail100%Healthy24h 99.95%
- p50
- 521ms
- p99
- 2.63s
- Throughput
- 41 tps
- Context
- 524K
- $/Mtok
- $0.350 / $1.00
parasail/fp8fp8 - DigitalOcean99.89%Healthy24h 98.75%
- p50
- 567ms
- p99
- 4.17s
- Throughput
- 8.0 tps
- Context
- 128K
- $/Mtok
- $0.200 / $0.696
digitalocean
Measured 3m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.