Devstral-2-123B-Instruct-2512: context, access and model facts

Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.

Coverage & sources ↗

Current catalog answers

What to know about Devstral-2-123B-Instruct-2512

AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.

Which Devstral-2-123B-Instruct-2512 does this page describe?

Devstral-2-123B-Instruct-2512 is a model record from Mistral AI in the Devstral family. Source

The recorded model identifier or checkpoint is 25.12. Use that exact identifier when checking documentation or a provider listing. Source

How can you access Devstral-2-123B-Instruct-2512?

The catalog documents API and Open weights access for Devstral-2-123B-Instruct-2512. Source

As of the catalog check, this version was marked deprecated. Source Check the linked lifecycle information before starting a new integration.

For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.

Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.

What are Devstral-2-123B-Instruct-2512's context and output limits?

The documented context window is 256,000 tokens. Source

A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.

Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.

What dates are documented for Devstral-2-123B-Instruct-2512?

Release date: December 9, 2025. Source This is a release milestone, not a knowledge or training cutoff. The source labels this “Release date on Mistral model specification.”

Neither a knowledge cutoff nor a training-data cutoff is established here. A release date, repository upload or filename cannot supply those missing dates.

What license is recorded for Devstral-2-123B-Instruct-2512?

The recorded license label is Modified MIT. Source

Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.

What is documented about the Devstral-2-123B-Instruct-2512 checkpoint?

This evidence refers to mistralai/Devstral-2-123B-Instruct-2512 at recorded revision 1613bf01adb5e1c6fdc196b46e6b173eae75eb4a, checked October 23, 2026. Repository metadata

Safetensors metadata records 125,025,989,840 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata

Recorded architecture class: Ministral3ForCausalLM. Repository metadata

Listed library: vllm. Check that library's version and model support before loading the weights. Repository metadata

Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata

What the configuration file says

The pinned config.json contains these values. Pinned configuration

max_position_embeddings: 262,144
torch_dtype: bfloat16
num_attention_heads: 96
num_key_value_heads: 8
num_hidden_layers: 88
hidden_size: 12,288

Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.

Read the retrieved model card for setup and qualifications. Model card

Keep the exact version in view

Other Devstral models from Mistral AI.

These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.

Devstral-Small-2-24B-Instruct-2512

API · Open weights · 256,000 context tokens

Devstral Medium 1.0

API · 128,000 context tokens

Devstral-Small-2507

API · Open weights · 128,000 context tokens

Devstral-Small-2505

API · Open weights · 128,000 context tokens

The documented record

Specifications, with their sources.

A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.

Publisher: Mistral AISource ↗
Family: DevstralSource ↗
Version: 25.12Source ↗
Availability: DeprecatedSource ↗
Access: API · Open weightsSource ↗
Inputs: Not documented
Outputs: Not documented
Context window: 256,000 tokensSource ↗
Maximum input: Not documented
Maximum output: Not documented
Knowledge cutoff: Not documented
Training-data cutoff: Not documented
Training completed: Not documented
Release date: Dec 9, 2025Release date on Mistral model specification · day precisionSource ↗
License: Modified MITSource ↗
Input price / 1M tokens: Not documented
Output price / 1M tokens: Not documented

Read this with the numbers.

Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. Lifecycle status refers to the Mistral API; publicly listed weights may remain usable under their license. Mistral context shorthand 256k is represented in nominal decimal tokens. Publisher repository evidence (2026-10-23): Published architecture metadata: Ministral3ForCausalLM. Repository library label: vllm. Published safetensors metadata counts 125,025,989,840 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published configuration: max_position_embeddings=262144; dtype=bfloat16; 88 hidden layers. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.

Model identifiers and aliases 1

mistralai/Devstral-2-123B-Instruct-2512

Follow the evidence

Official sources.

Devstral 2 specifications ↗docs.mistral.ai
Devstral-2-123B-Instruct-2512 — official model card ↗huggingface.co
Devstral-2-123B-Instruct-2512: official publisher repository metadata ↗huggingface.co
Devstral-2-123B-Instruct-2512: publisher model card at revision 1613bf01adb5 ↗huggingface.co
Devstral-2-123B-Instruct-2512: published checkpoint configuration at revision 1613bf01adb5 ↗huggingface.co

From the Headless Thrones newsroom

Editorial about Devstral-2-123B-Instruct-2512

No published articles are linked to this exact model yet. New coverage will appear here as it is published.

Your starting point

Devstral-2-123B-Instruct-2512

Mistral AI · API / Open weights

Browse all models ↗

Inputs: Not documented
Outputs: Not documented
Context window: 256,000 tokensSource ↗
Knowledge cutoff: Not documented

A place to begin comparing

0 models to consider.

Matches must share an access route, support every documented input type of your starting model, and return text. When both publish a context limit in the same field, the candidate must fall between half and twice that limit. Unknown or differently defined limits remain as broader matches, after verified near-context matches. Within each group, recent documented releases appear first. These criteria do not establish equal quality. The full current inventory is considered.

No candidate meets the documented access, input/output and context criteria. You can still choose models manually in the comparison tool.

A record you can follow

The source belongs beside the fact.

Official sources

Model records cite the developer’s documentation, release notes and model cards. A listing alone is not a tested service or a recommendation.

Dates mean different things

Knowledge cutoff, training-data cutoff, training completion and release date are separate fields. A model’s name or repository upload date does not establish any of them.

Limits need context

Some publishers use rounded K/M token figures. Deployment, reasoning settings and regional access can change usable limits. Read the source before choosing.

Coverage and last check

Independent editorial model library assembled from primary vendor documentation and official publisher model cards. This is a dated, auditable inventory of the sources reviewed, not a claim to every model worldwide. First-party language-model inventory for OpenAI, Anthropic, Google Gemini/Gemma, xAI, Meta and Reflection. Includes vendor-listed legacy/retired identities with explicit statuses; official pretrained and instruction-tuned checkpoints remain distinct. Excludes embeddings, moderation/guard models, image/audio/video-only generation, community fine-tunes, speculative draft helpers, format/runtime/quantization duplicates, and PaliGemma dataset-specific benchmark fine-tunes. Availability means documented vendor API or downloadable official weights, not guaranteed account eligibility. Unknown specifications and dates remain null. Rounded K/M limits preserve vendor granularity; exact integers are used only where documented. No OpenRouter facts are used. Primary-source inventory of language-capable models from Alibaba/Qwen, DeepSeek, Moonshot, MiniMax, Z.ai, ByteDance Seed, Tencent, Baidu, Xiaomi, StepFun, 01.AI, Shanghai AI Laboratory, Baichuan and OpenBMB. Includes full reachable official public weight inventories plus documented hosted API models and explicit retirements. Embeddings, reward/classifier/router/tokenizer/draft-head components, standalone OCR/document converters and image/video/audio-only generators are excluded; multimodal language models retained. Official packaging variants are folded into aliases where a canonical listing was identifiable; remaining research/base/SFT variants retain exact identities. Not a guarantee every historical/private/regional model is available. Unknown specifications remain null; K/M API display quantities use decimal normalization where explicitly noted, rather than implying verified exact serving ceilings. Model-name dates and repository creation timestamps are never used as release/training dates. Open weights does not mean unrestricted or OSI-open-source licensing. Some model-card bodies were unreachable; their public inventory metadata is retained and disclosed. Official Mistral, Cohere, AI21, NVIDIA Nemotron, Microsoft Phi/MAI, Amazon Nova, IBM Granite, AllenAI OLMo/Molmo, TII Falcon, Nous Research, Arcee and Essential AI model inventory checked 2026-10-23. Includes base, instruction, reasoning, coding and text-producing multimodal models, including legacy API versions. Excludes embeddings/rerankers/reward and safety classifiers, image/audio/video-only generation, robotics-only models, duplicate quantization/runtime packages, adapters, intermediate checkpoint experiments, and third-party mirrors. Arcee coverage focuses on its named product families rather than exploratory merge repositories. Repository listing means listed, not independently verified API availability. K/M figures are nominal decimal normalizations when the source supplies shorthand; deployment-specific exact token limits may differ. Unverified values remain null. This is a source-backed inventory, not a complete claim-level independent editorial review. Supplemental official Liquid AI, Reka and Inception generative language catalog. Excludes media-only generators and decision/classification-only models. No assumed training dates.

Catalog edition updated Oct 23, 2026. Source links are provided on each model record.

View the full coverage report and discovery sources ↗