Back
Mistral: Mistral Nemo
Mistral
Input: text
Output: text
Released: Jul 19, 2024•Updated: Mar 28, 2025
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.
It supports function calling and is released under the Apache 2.0 license.
131,072 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| kluster.ai | klusterAi | 131K | 131K | $0.02/M | $0.07/M | 107.3 t/s | 738 ms |
| Enfer | enfer | 131K | 66K | $0.03/M | $0.07/M | 58.2 t/s | 6404 ms |
| NextBit | nextBit | 128K | - | $0.03/M | $0.07/M | 42.8 t/s | 1556 ms |
| DeepInfra | deepInfra | 131K | 16K | $0.04/M | $0.08/M | 54.9 t/s | 251 ms |
| inference.net | inferenceNet | 16K | 16K | $0.04/M | $0.10/M | 59.6 t/s | 992 ms |
| Nebius AI Studio | nebiusAiStudio | 128K | - | $0.04/M | $0.12/M | 33.1 t/s | 603 ms |
| NovitaAI | novitaAi | 131K | - | $0.04/M | $0.17/M | 42.1 t/s | 1173 ms |
| Atoma | atoma | 128K | 80K | $0.10/M | $0.10/M | 60.8 t/s | 646 ms |
| Parasail | parasail | 131K | 131K | $0.11/M | $0.11/M | 90.9 t/s | 747 ms |
| Mistral | mistral | 131K | - | $0.15/M | $0.15/M | 143.8 t/s | 219 ms |
| Azure | azure | 128K | - | $0.30/M | $0.30/M | 98.6 t/s | 1146 ms |
Standard Pricing
Input Tokens
$0.000000025
per 1K tokens
Output Tokens
$0.00000007
per 1K tokens