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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | deepInfra | 131K | 16K | $0.01/M | $0.03/M | 52.2 t/s | 234 ms |
| Kluster | klusterAi | 131K | 131K | $0.01/M | $0.03/M | 93.7 t/s | 915 ms |
| Enfer | enfer | 131K | 131K | $0.02/M | $0.07/M | 39.9 t/s | 1147 ms |
| Parasail | parasail | 131K | 131K | $0.03/M | $0.11/M | 147.3 t/s | 387 ms |
| NextBit | nextBit | 128K | - | $0.03/M | $0.07/M | 45.6 t/s | 1595 ms |
| InferenceNet | inferenceNet | 16K | 16K | $0.04/M | $0.10/M | 64.7 t/s | 928 ms |
| Nebius | nebiusAiStudio | 128K | - | $0.04/M | $0.12/M | 44.4 t/s | 507 ms |
| Novita | novitaAi | 60K | 32K | $0.04/M | $0.17/M | 60.0 t/s | 1087 ms |
| InoCloud | inoCloud | 131K | 131K | $0.07/M | $0.07/M | 101.4 t/s | 1297 ms |
| Mistral | mistral | 131K | - | $0.15/M | $0.15/M | 107.8 t/s | 253 ms |
| Azure | azure | 128K | - | $0.30/M | $0.30/M | 101.1 t/s | 1129 ms |
Standard Pricing
Input Tokens
$0.00000001
per 1K tokens
Output Tokens
$0.000000028
per 1K tokens