Deepinfra
100.00%Context131.1K
Max output131.1K
p50 latency341 ms
Throughput24.5 t/s
Input price$0.02
Output price$0.04
Zero retentionNo training
Model directory
Baseer model profileLanguage model
mistral/mistral-nemo
Mistral Nemo 12B
12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
Input / 1M tokens$0.02
Output / 1M tokens$0.04
Maximum context131.1K
Inference providers3
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Mistral
100.00%Context128K
Max output128K
p50 latency311 ms
Throughput123.5 t/s
Input price$0.15
Output price$0.15
Zero retentionNo training
Novita
100.00%Context60.3K
Max output16K
p50 latency250 ms
Throughput64.0 t/s
Input price$0.04
Output price$0.17
No training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 131.1K | 131.1K | 341 ms | 24.5 t/s | 100.000% | $0.02 | $0.04 | |
Mistral | 128K | 128K | 311 ms | 123.5 t/s | 100.000% | $0.15 | $0.15 | |
Novita | 60.3K | 16K | 250 ms | 64.0 t/s | 100.000% | $0.04 | $0.17 |
What can this model do?
Available modalities and capabilities across inference providers.
TextTool useVisionTools
Technical profile
- Model type
- Language model
- Release date
- Jul 18, 2024
- Knowledge cutoff
- 2024-04
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
mistral/mistral-nemoModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.