Mistral AI · Devstral 2 123b Instruct 2512 · active
Devstral-2-123B-Instruct-2512
Devstral-2-123B-Instruct-2512 is an open-weight language model published by Mistral AI.
mistralai/Devstral-2-123B-Instruct-2512Provider availability
Serving endpoints and pricing
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Release date
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Comparable peers
Related model comparisons
Questions
Devstral-2-123B-Instruct-2512 FAQs
What is Devstral-2-123B-Instruct-2512?+
Devstral-2-123B-Instruct-2512 is an open-weight language model published by Mistral AI. It is developed by Mistral AI and its current sourced lifecycle status is active.
What inputs and outputs does Devstral-2-123B-Instruct-2512 support?+
Devstral-2-123B-Instruct-2512's current record lists Text as input and Text as output.
How much context does Devstral-2-123B-Instruct-2512 support?+
The current record lists a 262,144-token context window and does not report a maximum output length.
Is Devstral-2-123B-Instruct-2512 available through an API?+
Devstral-2-123B-Instruct-2512's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is Devstral-2-123B-Instruct-2512?+
The current record lists 125B total parameters and an unknown active parameter count. Its architecture is Ministral3ForCausalLM.
What capabilities and tasks does Devstral-2-123B-Instruct-2512 support?+
Devstral-2-123B-Instruct-2512's recorded capabilities are chat, generation, and tools. Its supported tasks are text.
Can Devstral-2-123B-Instruct-2512 be self-hosted?+
Devstral-2-123B-Instruct-2512 is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Devstral-2-123B-Instruct-2512 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are mistralai/Devstral-2-123B-Instruct-2512.
Which models can Devstral-2-123B-Instruct-2512 be compared with?+
The current compatible peer set includes NVIDIA-Nemotron-3-Super-120B-A12B-BF16, Qwen3-Coder-Next, Qwen3-Coder-Next-Base, gpt-oss-120b, and command-a-plus-05-2026-bf16. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for Devstral-2-123B-Instruct-2512?+
Devstral-2-123B-Instruct-2512 was last verified Aug 28, 2026 from Mistral AI's primary source, “mistralai/Devstral-2-123B-Instruct-2512 developer model repository.” The evidence is classified as official fact.
Primary evidence