Models/Mistral AI/Mixtral 8x7B v0.1

Mixtral 8x7B v0.1

Mistral AI 🧠 Language Model

Open MoE Mistral with 8 experts × 7B. Strong all-rounder. Hosted via Together.

Specifications

Context Window32,768 tokens
Max Output4,096 tokens
Speed●●●●● Fast
ModalitiesInput: text  ·  Output: text
FeaturesTools: No Streaming: No

Pricing

Contact for pricing

Capabilities

chat
Use Mixtral 8x7B v0.1 on Zubnet →

More from Mistral AI

Mistral 7B v0.1
Original open Mistral 7B Instruct (v0.1). Classic foundation model. Hosted via Together.
🧠 Language Model
Mistral 7B v0.3
Improved open Mistral 7B Instruct (v0.3). Better instruction following. Hosted via Together.
🧠 Language Model
Mistral Large 3
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
🧠 Language Model
Mistral Small 24B (2501)
Open release of Mistral Small 24B. Strong reasoning at low cost. Hosted via Together.
🧠 Language Model