Nvidia
Devstral-2-123B-Instruct-2512 Pricing
API pricing for Devstral-2-123B-Instruct-2512 by Nvidia. Input tokens cost $0/1M, output tokens cost $0/1M with 262K context window.
Last updated:
ReasoningToolsVision
Input Cost
$0
per 1M tokens
Output Cost
$0
per 1M tokens
Context Window
262K
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Provider
Nvidia
Model ID
mistralai/devstral-2-123b-instruct-2512
Context Window
262K tokens
Max Output
262144 tokens
Release Date
2025-12-08
Sources
Compare Alternatives
| Model | Input | Output | Context |
|---|---|---|---|
| Devstral-2-123B-Instruct-2512 (this model) | $0 | $0 | 262K |
| text-embedding-3-small OpenAI | $0.02 | $0 | 8K |
| Qwen3-ASR Flash Alibaba (China) | $0.032 | $0.032 | 53K |
| Qwen3-ASR Flash Alibaba | $0.035 | $0.035 | 53K |
| Ministral 3B Mistral | $0.04 | $0.04 | 128K |
| Mistral Embed Mistral | $0.1 | $0 | 8K |
Available from Resellers
Devstral-2-123B-Instruct-2512 is also available through these resellers and gateways:
| Reseller | Model | Input | Output |
|---|---|---|---|
| Chutes | Devstral 2 123B Instruct 2512 | $0.05 | $0.22 |
| Cortecs | Devstral 2 2512 | $0 | $0 |
| Cortecs | Devstral Small 2 2512 | $0 | $0 |
| NanoGPT | Devstral 2 123b Instruct 2512 | $1 | $2 |
| NanoGPT | Ministral 14b Instruct 2512 | $1 | $2 |
| NanoGPT | Mistral Large 3 675b Instruct 2512 | $1 | $2 |
| OpenRouter | Devstral 2 2512 | $0.15 | $0.6 |
| OpenRouter | Devstral 2 2512 (free) | $0 | $0 |
| Scaleway | Devstral 2 123B Instruct (2512) | $0.4 | $2 |