Llama 4 Maverick: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | — | 99.26% | 99.26% | — | — | — | 1.0M | $0.200 / $0.800◆ (best) | |
DigitalOceandigitalocean | No data | — | — | 99.71% | 99.71% | — | — | — | 128K | $0.200 / $0.696◆ (best) |
Googlegoogle-vertex/us-east5 | No data | — | — | 99.55% | 99.55% | — | — | — | 524K | $0.350 / $1.15 |
| No data | — | — | 99.24% | 99.24% | — | — | — | 1.0M | $0.270 / $0.850 | |
| No data | — | — | 99.88%◆ (best) | 99.88%◆ (best) | — | — | — | 524K | $0.350 / $1.00 |
- No data24h —
- 7d
- 99.26%
- 30d
- 99.26%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.800◆ (best)
deepinfra/basefp8 - No data24h —
- 7d
- 99.71%
- 30d
- 99.71%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.200 / $0.696◆ (best)
digitalocean - No data24h —
- 7d
- 99.55%
- 30d
- 99.55%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 524K
- $/Mtok
- $0.350 / $1.15
google-vertex/us-east5 - No data24h —
- 7d
- 99.24%
- 30d
- 99.24%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.270 / $0.850
novita/fp8fp8 - No data24h —
- 7d
- 99.88%◆ (best)
- 30d
- 99.88%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 524K
- $/Mtok
- $0.350 / $1.00
parasail/fp8fp8
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
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.
Throughput
Median tokens per second.