Home / LLM Inference / Fireworks AIFFireworks AIProduction inference for open modelsReviewed byRoman KAboutFast, cost-efficient inference and fine-tuning for Llama, Mixtral, FireFunction, and DeepSeek.inferenceopen-modelsfunction-callingMetricsMore in LLM InferenceGroqFastest LLM inference on LPUsTogether AIRun open-source models in productionOpenRouterUnified API for hundreds of LLMsModalServerless GPUs and containers