Using Llama 3.1 70B Instruct on IBM watsonx

Implementation guide · Llama 3.1 · AI at Meta

ServerlessOpen Weights

IBM watsonx exposes Llama 3.1 70B Instruct through model ID llama3.1-70b-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-09. Next refresh: weekly.

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 llama3.1-70b-instruct — see the documentation for request format.
  3. 3
    You'll be billed $0.80/1M input, $2.40/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

See IBM watsonx documentation for integration details.

Pricing on IBM watsonx

TypePrice (per 1M)
Input tokens$0.80
Output tokens$2.40

Capabilities

Structured Outputs

About Llama 3.1 70B Instruct

The Llama 3.1 70B Instruct model is a cutting-edge large language model with 70 billion parameters, designed for instruction-following tasks. It features multilingual capabilities, supporting languages like English, German, French, and others. Fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF), it excels in understanding and responding to user instructions. The model can handle a context length of up to 128k tokens, making it suitable for complex dialogue systems and applications requiring detailed responses.

Full model details →

Model Specs

Released2024-07-23
Parameters70B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2023-12

More Models on IBM watsonx

Llama 3.1 405B InstructLlama 3.1 8B Instruct
All models on IBM watsonx →

Also available on(13)

Hyperbolic AI Inference$0.40/1MDeepInfra$0.40/1MOpenRouter$0.40/1M
Compare all providers →

Provider

IBM watsonx

IBM

Armonk, New York, United States