Devstral 2 123B API
About
Process massive datasets with Devstral 2 123B, featuring an expansive 262K context window for long-document analysis. This model delivers cost-effective pricing at $0.40/1M input and $1.40/1M output tokens, open weights architecture. Access Devstral 2 123B via the NanoGPT API with up to 66K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.40
Output
$1.40
Caching (per 1M tokens)
Read
$0.20
Frequently Asked Questions
Devstral 2 123B by NanoGPT costs $0.40 per 1M input tokens and $1.40 per 1M output tokens. Cached reads cost $0.20 per 1M tokens.
Model Details
ID
mistralai/devstral-2-123b-instruct-2512
Provider
NanoGPTFamily
devstral
Release Date
Dec 9, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NANO_GPT_API_KEY
API Base URL
https://nano-gpt.com/api/v1