Ministral 8B
High-volume, simple tasks like tagging, routing, and short extraction.
What are Ministral 8B's specs and price?
Ministral 8B, built by Mistral, ships a 131K-token context window and a 16K-token max output, released 2025-10. It supports text input and costs $0.15 per million blended tokens, the 4th-cheapest of 32 models we track.
Specs
| Context window | 131K tokens |
| Max output | 16K tokens |
| Modalities | text |
| Extended thinking | No |
| Released | 2025-10 |
| Knowledge cutoff | 2025-07 |
| Provider | Mistral |
Verified 2026-08-08 — source.
Where it ranks
Strengths
- Ultra-cheap edge-class model
- Very low latency
- Good for simple, repetitive tasks
More about Ministral 8B
FAQ
What is Ministral 8B's context window?
Ministral 8B has a 131K-token context window and a 16K-token max output — the 28th-largest context of the 32 current models we track. Source: https://docs.mistral.ai/getting-started/models/, verified 2026-08-08.
Does Ministral 8B support vision or audio input?
No — Ministral 8B is text-only as of 2026-08-08.
Does Ministral 8B have a reasoning or extended-thinking mode?
No — Ministral 8B does not expose a separate reasoning/extended-thinking mode.
When was Ministral 8B released, and what is its knowledge cutoff?
Ministral 8B was released 2025-10 with a knowledge cutoff of 2025-07.
How much does Ministral 8B cost, and who provides it?
Ministral 8B is served by Mistral at $0.15/M blended tokens (3:1 input:output) — the 4th-cheapest of 32 current models. Full pricing breakdown: /llm-api-pricing/ministral-8b.