Currently listed through these providers:
Model details
Ministral 8B
Ministral 8B is a compact model from the Mistral family designed to run efficiently on edge devices and lightweight infrastructure. Its defining architectural feature is an interleaved sliding-window attention pattern that prioritises memory efficiency and lower latency over the full context window, making it well suited to local or constrained deployments where larger frontier models are impractical.
In practical terms, the model combines that efficient attention design with broad multimodal capability, accepting both text and image inputs while producing text output. Tool use is supported alongside vision, and the long context window enables it to handle substantial documents, multi-turn conversations, or agentic workflows that involve attached media. With open weights and an approachable size, Ministral 8B fits well for developers building on-device assistants, retrieval-augmented applications, and vision-aware tools that need a fast, self-hostable backbone rather than a heavy cloud-only system.
Quick Info
Powered by- Provider
- DevPass (LLM Gateway)
- 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
- 8,192 tokens
- Context window
- 262,144 tokens
Transparent token rates
Compare mistral pricing
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Latest news about Ministral 8B
No articles yet. Fetch the latest news to show it here.