Mistral Nemo: 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) | 99.93% | 99.93%◆ (best) | 99.93%◆ (best) | 505ms | 2.06s◆ (best) | 27 tps◆ (best) | 131K | $0.030 / $0.030 | |
| Healthy | 99.08% | 98.57% | 98.42% | 98.42% | 349ms◆ (best) | 3.80s | 24 tps | 131K | $0.019 / $0.030◆ (best) | |
| Degraded | 96.49% | 95.36% | 96.50% | 96.50% | 967ms | 6.24s | 13 tps | 128K | $0.044 / $0.160 | |
| Down | 43.62% | 58.41% | 57.83% | 57.83% | 4.75s | 59.2s | 6.0 tps | 60K | $0.040 / $0.170 |
- Parasail100%◆ (best)Healthy24h 99.93%
- 7d
- 99.93%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- 505ms
- p99
- 2.06s◆ (best)
- Throughput
- 27 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.030 / $0.030
parasail/fp8fp8 - DeepInfra99.08%Healthy24h 98.57%
- 7d
- 98.42%
- 30d
- 98.42%
- p50
- 349ms◆ (best)
- p99
- 3.80s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030◆ (best)
deepinfra/fp8fp8 - Io Net96.49%Degraded24h 95.36%
- 7d
- 96.50%
- 30d
- 96.50%
- p50
- 967ms
- p99
- 6.24s
- Throughput
- 13 tps
- Context
- 128K
- $/Mtok
- $0.044 / $0.160
io-net/fp16fp16 - Novita43.62%Down24h 58.41%
- 7d
- 57.83%
- 30d
- 57.83%
- p50
- 4.75s
- p99
- 59.2s
- Throughput
- 6.0 tps
- Context
- 60K
- $/Mtok
- $0.040 / $0.170
novita/fp8fp8
Measured 4m 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.