Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Mistral logo

Model details

Ministral 3 8B

Ministral 3 8B belongs to the Ministral 3 family, which is explicitly designed for edge deployment and engineered to run across a wide spectrum of hardware, from modest laptops to more capable workstations. The family ships in multiple size variants, with the 8B tier offering a middle-ground balance between capability and resource efficiency for on-device inference. Its family-level positioning as an edge-oriented release reflects a broader industry trend toward smaller, self-contained models that can operate without dependence on remote serving infrastructure.

The Ministral 3 family is published with a vision tag alongside its size selectors, signaling that the lineup supports image-conditioned inputs as part of its multimodal intent. For the 8B variant specifically, this implies suitability for lightweight assistant and document-understanding workloads that benefit from visual context but still need to fit within constrained local memory budgets. As an open-weights release intended for edge use, it is a practical fit for developers building private, local-first applications that need a capable general-purpose model without relying on hosted inference.

Mistralministral-8b-2512ministral

Quick Info

Powered by
Provider
Mistral
Model key
ministral-8b-2512
Release date
Dec 2, 2025
Last updated
Dec 2, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.15
Output token cost
$0.15

Limits

Output tokens
262,144 tokens
Context window
262,144 tokens

Transparent token rates

Compare Ministral 3 8B pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Ministral 3 8B

Mistral

Official sourceAnnouncement

Mistral AI announced Mistral 3 on December 2, 2025, releasing a new generation of small, dense models in 14B, 8B, and 3B sizes alongside the new Mistral Large 3 mixture-of-experts model. All Mistral 3 models, including the 8B, are open-sourced under the Apache 2.0 license to empower the developer community. The Ministral models are positioned as offering the best performance-to-cost ratio in their category within the Mistral 3 family. The full lineup was trained on NVIDIA Hopper GPUs, with the broader launch accompanied by partnerships with NVIDIA, vLLM, and Red Hat to deliver optimized checkpoints and faster accessibility.

Videos about Ministral 3 8B

More models around Ministral 3 8B