Scan to contactDevstral 2 (latest)
Devstral 2 (latest) is a devstral model from Mistral for assistants, generation and automation tasks
Devstral 2 (latest) is a large language model from Mistral, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.
starsCapabilities
codeFunction callingstreamStreaming output
paymentsContext and pricing
Context limit262,144
Max output262,144
Knowledge cutoff2025-12
Input price$0.4/ 1M tokens
Output price$2/ 1M tokens
descriptionOverview
Overview
Devstral 2 (latest) is a model from Mistral with model ID devstral-medium-latest. This wiki entry helps compare its positioning, pricing signals, common use cases and relay availability.
Best for
Use Devstral 2 (latest) as a candidate when comparing context length, input/output pricing, tool support, multimodal capability and real-world latency.
lightbulbUse cases
- Assistants and customer support
- Content generation and rewriting
- Knowledge Q&A and summarization
- Structured extraction
thumb_upStrengths
- Useful for common language tasks
- Easy to compare with related models
- Can be evaluated with pricing and relay availability
- Good candidate for model selection
infoLimitations
- Exact capability depends on provider implementation
- Pricing and availability can change
- Complex tasks still need evaluation
- Auto-generated content should be checked against official sources