llmreference

Using Mixtral 8x7B on Bitdeer AI

Implementation guide · Mixtral · MistralAI

Serverless

Quick Start

  1. 1
    Create an account at Bitdeer AI and generate an API key.
  2. 2
    Use the Bitdeer AI SDK or REST API to call mixtral-8x7b — see the documentation for request format.
  3. 3
    You'll be billed $0.18/1M input, $0.54/1M output tokens. See full pricing.

Code Examples

See Bitdeer AI documentation for integration details.

About Bitdeer AI

Bitdeer AI Cloud offers both serverless (pay-per-use) and dedicated (reserved GPU) deployment options for LLM inference. The platform provides OpenAI-compatible API endpoints and supports fine-tuning on dedicated instances. Models are hosted on NVIDIA H100/H200/A100 GPUs with automatic scaling.

Bitdeer Technologies Group is a Singapore-based AI infrastructure and cloud computing company. The company provides AI Cloud, a serverless and dedicated inference platform for deploying and scaling LLM and generative AI models.

Pricing on Bitdeer AI

TypePrice (per 1M)
Input tokens$0.18
Output tokens$0.54

Capabilities

No model capability flags are currently sourced.

About Mixtral 8x7B

Mixtral 8x7B, developed by Mistral AI, features a cutting-edge Mixture of Experts (MoE) architecture, utilizing eight experts with seven billion parameters each, yielding a total of 46.7 billion parameters. This architecture activates only two experts per token, allowing for efficient processing and a 6x faster inference rate compared to Llama 2 70B. The model excels in performance, surpassing Llama 2 70B and competing with GPT-3.5 on numerous benchmarks. It supports multiple languages and can handle context up to 32,000 tokens, enhancing understanding of lengthy text. Designed for diverse tasks, it is strong in code generation and available under a permissive Apache 2.0 license, promoting community engagement. Compatible with various optimization tools, its weights are easily deployable, with Mistral AI continuing to improve its capabilities through performance optimizations and fine-tuning efforts.

Model Specs

Released2023-12-11
Parameters8x7B
Context32K
ArchitectureMixture of Experts
Knowledge cutoff2023-12

Provider

Bitdeer AI

Bitdeer Technologies Group

Singapore