Mistral Batch API Release

Mistral AI has introduced a Batch API to provide a more cost-effective method for processing high-volume data requests. This new capability allows developers to process large datasets at 50% of the cost of standard synchronous API calls, making frontier AI more affordable for scale-intensive applications.

Cost Reduction and Efficiency

The Batch API reduces operational costs by 50% compared to synchronous API calls. It is designed for AI applications where the volume of data processed is more critical than the immediacy of the response. Instead of waiting for real-time answers, users upload a batch file containing multiple requests, and once the processing is complete, they download the resulting output file.

Supported Models and Limits

The Batch API is currently available for all models served on La Plateforme. Mistral AI has also stated that the feature will be coming soon to their cloud provider partners. Usage is currently limited to 1 million ongoing requests per workspace.

Primary Use Cases

The Batch API is optimized for asynchronous, high-volume tasks. Key applications include:

  • Data Analysis: Performing sentiment analysis and processing customer feedback at scale.

  • Content Processing: Executing bulk document summarization and translation.

  • Search Infrastructure: Generating vector embeddings to prepare search indexes.

  • Data Management: Large-scale data labeling.

Sources

Related

  • Dispatch
    Mistral Code Release Notes

    Mistral AI has launched Mistral Code, a vertically integrated AI coding assistant for enterprises that combines frontier models with an in-IDE assistant and flexible deployment options.

  • Dispatch
    Mistral AI La Plateforme Release

    Mistral AI has launched La Plateforme, a beta API service providing access to three generative chat endpoints and one embedding endpoint with varying performance and price tradeoffs.

  • Dispatch
    Mistral Medium 3 Release Notes

    Mistral AI has released Mistral Medium 3, a frontier-class model that balances state-of-the-art performance with 8x lower costs and flexible enterprise deployment options.

  • Dispatch
    Mistral AI September 2024 Release

    Mistral AI has introduced a free tier for la Plateforme, significant price reductions across its model family, the Mistral Small v24.09 model, and free vision capabilities via Pixtral 12B on le Chat.

  • Dispatch
    Mistral Agents API Release

    Mistral AI has launched the Agents API, a framework that combines language models with built-in connectors, persistent memory, and multi-agent orchestration to enable the creation of active problem-solving AI agents.