Fireworks.ai becomes a supported Inference Provider on Hugging Face Hub

AI Impact Summary

Fireworks.ai is now a supported Inference Provider on HF Hub, enabling serverless inference directly on model pages and via HF libraries. Developers can route requests to Fireworks.ai using the InferenceClient with provider 'fireworks-ai', with models like deepseek-ai/DeepSeek-R1 and llama-v3p3-70b-instruct demonstrated, reducing operational overhead but introducing an external dependency. This change affects billing and credential management for inference workloads, offering direct Fireworks credits for some usage and hub-routed pricing for others.