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) | 99.94% | 99.92%◆ (best) | 99.92%◆ (best) | 457ms | 2.05s◆ (best) | 28 tps◆ (best) | 131K | $0.030 / $0.030 | |
| Healthy | 99.29% | 98.55% | 98.41% | 98.41% | 362ms◆ (best) | 3.55s | 24 tps | 131K | $0.019 / $0.030◆ (best) | |
| Degraded | 90.87% | 95.46% | 96.62% | 96.62% | 567ms | 6.34s | 12 tps | 128K | $0.042 / $0.160 | |
| Down | 28.70% | 58.44% | 58.11% | 58.11% | 19.0s | 62.0s | 2.0 tps | 60K | $0.040 / $0.170 |
- Parasail100%◆ (best)Healthy24h 99.94%
- 7d
- 99.92%◆ (best)
- 30d
- 99.92%◆ (best)
- p50
- 457ms
- p99
- 2.05s◆ (best)
- Throughput
- 28 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.030 / $0.030
parasail/fp8fp8 - DeepInfra99.29%Healthy24h 98.55%
- 7d
- 98.41%
- 30d
- 98.41%
- p50
- 362ms◆ (best)
- p99
- 3.55s
- Throughput
- 24 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030◆ (best)
deepinfra/fp8fp8 - Io Net90.87%Degraded24h 95.46%
- 7d
- 96.62%
- 30d
- 96.62%
- p50
- 567ms
- p99
- 6.34s
- Throughput
- 12 tps
- Context
- 128K
- $/Mtok
- $0.042 / $0.160
io-net/fp16fp16 - Novita28.70%Down24h 58.44%
- 7d
- 58.11%
- 30d
- 58.11%
- p50
- 19.0s
- p99
- 62.0s
- Throughput
- 2.0 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.