MythoMax 13B: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.97% | 99.98%◆ (best) | 99.97%◆ (best) | 235ms◆ (best) | 1.34s | 45 tps | 4K | $0.400 / $0.400 | |
| Healthy | 100%◆ (best) | 99.87% | 99.90% | 99.92% | 368ms | 1.79s | 69 tps | 8K | $0.350 / $0.600 | |
| Healthy | 100%◆ (best) | 99.97% | 99.98% | 99.94% | 382ms | 964ms◆ (best) | 97 tps◆ (best) | 4K | $0.080 / $0.110 | |
| No data | — | — | — | 99.90% | — | — | — | 4K | $0.060 / $0.060◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 99.97%
- 7d
- 99.98%◆ (best)
- 30d
- 99.97%◆ (best)
- p50
- 235ms◆ (best)
- p99
- 1.34s
- Throughput
- 45 tps
- Context
- 4K
- $/Mtok
- $0.400 / $0.400
deepinfra/fp16fp16 - Mancer 2100%◆ (best)Healthy24h 99.87%
- 7d
- 99.90%
- 30d
- 99.92%
- p50
- 368ms
- p99
- 1.79s
- Throughput
- 69 tps
- Context
- 8K
- $/Mtok
- $0.350 / $0.600
mancer/fp8fp8 - Parasail100%◆ (best)Healthy24h 99.97%
- 7d
- 99.98%
- 30d
- 99.94%
- p50
- 382ms
- p99
- 964ms◆ (best)
- Throughput
- 97 tps◆ (best)
- Context
- 4K
- $/Mtok
- $0.080 / $0.110
parasail/fp16fp16 - No data24h —
- 7d
- —
- 30d
- 99.90%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 4K
- $/Mtok
- $0.060 / $0.060◆ (best)
nextbit/int4int4
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.