The request names Mistral's Devstral 2 2512 model, but none of the candidate sources is Mistral's own page, so no product here is the model itself. The closest sources are Replicate, which hosts open models through a cloud API 2, and Hugging Face, which hosts and serves models through its Hub and inference tools 4; both are relevant ways to run a hosted model.
A question back: Do you want to run Devstral 2 2512 through a hosted API, or download the weights and run them locally?
- 1
Replicatereplicate.comverified and signed
Runs open-source machine learning models, including Mistral-family models, through a cloud API 2.
+14 community tools built for it
for agents: qwen/qwen-image-2512 · mistralai/mistral-7b-v0.1 · lucataco/phixtral-2x2_8
- 2
Hugging Facehuggingface.cofound in code, not yet checked
Hosts and serves open models through its Hub, with inference access to many models 4.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: get_model · list_models · check_model_access
Sources
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 4Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
For agents: the 10 actions behind this answer
mistralai · Mixtral-8x22B-Instruct-v0.1 verified and signed
Task: MistralAI
qwen/qwen-image-2512 · qwen/qwen-image-2512 verified and signed
Qwen Image 2512 is an improved version of Qwen Image with more realistic human generation, finer textures, and stronger text rendering
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
get_model · dell-ai found in code, not yet checked
Get detailed information about a specific model.
find-stl · find-stl verified and signed
Search and download ready-to-print 3D model files (STL/3MF/ZIP) for a concept or specific part by querying Printables (first). Use when an agent needs to find an existing model, capture license/attribution, download the source files, and output a local folder + manifest for quoting/printing.
databricks-model-serving · databricks-model-serving verified and signed
Databricks Model Serving endpoint lifecycle and ops. Use when asked to: CRUD serving endpoints (CLI or MLflow Deployments client); configure traffic routing for A/B / canary deploys and zero-downtime version swaps; retrieve OpenAPI schemas; inspect logs, metrics, or permissions; manage legacy AI Gat
python · fastcore verified and signed
alter_model_version · gravitino found in code, not yet checked
Alter a specific version of a model.
XLNet · sentence-transformers verified and signed
export · export verified and signed
Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.