llmreference
IBM watsonx

Using Mixtral 8x7B on IBM watsonx

Implementation guide · Mixtral · MistralAI

Serverless

Quick Start

  1. 1
    Create an account at IBM watsonx and generate an API key.
  2. 2
    Use the IBM watsonx SDK or REST API to call mixtral-8x7b — see the documentation for request format.
  3. 3
    You'll be billed $0.60/1M input, $0.60/1M output tokens. See full pricing.

Code Examples

See IBM watsonx documentation for integration details.

About IBM watsonx

The IBM watsonx AI platform is a comprehensive solution that integrates generative AI capabilities with traditional machine learning. It offers users access to a wide range of foundation models, including both IBM-developed and third-party options. The platform features a user-friendly studio for model building, a robust data management system based on an open lakehouse architecture, and governance tools to ensure compliance and ethical AI practices. Watsonx supports hybrid cloud deployments, enabling seamless integration of AI workloads into existing infrastructures, which enhances operational efficiency and scalability. This AI platform empowers organizations to leverage artificial intelligence for data-driven decision-making and innovation across multiple sectors, including healthcare, finance, and customer service. It offers advanced analytics, natural language processing, and automated workflows, aiding in tasks such as predictive analytics, content generation, and customer engagement. By streamlining processes and providing actionable insights, the platform helps businesses improve productivity and gain a competitive advantage, making it a crucial tool for those looking to harness the full potential of AI in their operations.

IBM offers a comprehensive AI platform that includes IBM watsonx, a next-generation enterprise AI and data platform. The platform integrates various AI technologies and services, including natural language processing, machine learning, and data analytics. IBM's AI solutions are designed to help businesses across industries leverage artificial intelligence for improved decision-making, automation, and innovation. The company's focus on AI extends to areas such as cloud computing, quantum computing, and industry-specific applications, making it a leader in enterprise AI solutions.

Pricing on IBM watsonx

TypePrice (per 1M)
Input tokens$0.60
Output tokens$0.60

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

IBM watsonx
IBM watsonx

IBM

Armonk, New York, United States