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) | 99.86% | 99.71% | 99.16% | 375ms | 2.46s | 48 tps | 128K | $0.023 / $0.030 | |
| Healthy | 100%◆ (best) | 99.97% | 99.20% | 96.35% | 292ms◆ (best) | 1.07s | 96 tps◆ (best) | 131K | $0.030 / $0.030 | |
| Healthy | 99.95% | 99.93% | 99.94%◆ (best) | 99.92%◆ (best) | 833ms | 3.74s | 22 tps | 131K | $0.019 / $0.030 | |
| Healthy | 99.53% | 99.82% | 99.78% | 99.64% | 515ms | 4.35s | 30 tps | 131K | $0.018 / $0.030◆ (best) | |
| Down | 55.65% | 77.47% | 85.45% | 82.95% | 972ms | 14.5s | 40 tps | 60K | $0.040 / $0.170 | |
Mistralmistral/eu | No data | — | 98.03% | 99.78% | 99.74% | 485ms | 937ms◆ (best) | 67 tps | 131K | $0.150 / $0.150 |
Mistralmistral/zdr | No data | — | — | — | — | — | — | — | 131K | $0.165 / $0.165 |
- Io Net100%◆ (best)Healthy24h 99.86%
- 7d
- 99.71%
- 30d
- 99.16%
- p50
- 375ms
- p99
- 2.46s
- Throughput
- 48 tps
- Context
- 128K
- $/Mtok
- $0.023 / $0.030
io-net/fp16fp16 - Parasail100%◆ (best)Healthy24h 99.97%
- 7d
- 99.20%
- 30d
- 96.35%
- p50
- 292ms◆ (best)
- p99
- 1.07s
- Throughput
- 96 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.030 / $0.030
parasail/fp8fp8 - DeepInfra99.95%Healthy24h 99.93%
- 7d
- 99.94%◆ (best)
- 30d
- 99.92%◆ (best)
- p50
- 833ms
- p99
- 3.74s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.019 / $0.030
deepinfra/fp8fp8 - DekaLLM99.53%Healthy24h 99.82%
- 7d
- 99.78%
- 30d
- 99.64%
- p50
- 515ms
- p99
- 4.35s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.018 / $0.030◆ (best)
dekallm/fp8fp8 - Novita55.65%Down24h 77.47%
- 7d
- 85.45%
- 30d
- 82.95%
- p50
- 972ms
- p99
- 14.5s
- Throughput
- 40 tps
- Context
- 60K
- $/Mtok
- $0.040 / $0.170
novita/fp8fp8 - No data24h 98.03%
- 7d
- 99.78%
- 30d
- 99.74%
- p50
- 485ms
- p99
- 937ms◆ (best)
- Throughput
- 67 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.150
mistral/eu - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.165 / $0.165
mistral/zdr
Measured 1m 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, averaged over the hour.
Throughput
Median tokens per second.