Пополнение баланса
- Open models with optimized inference and an OpenAI-compatible API
- Usage-based token billing
- Your own fine-tuned models and dedicated deployments
Home / APIs & tokens / Fireworks AI
Fireworks
Plan contents as published by the vendor; seller prices arrive at launch.
Fireworks AI is a fast-inference platform for open models such as Llama, Qwen, DeepSeek and Mixtral, tuned for low latency and high throughput. It supports function calling, JSON-schema structured output, multimodal and audio models, image generation, and fine-tuning with deployment of your own LoRA. Dedicated deployments are available when you need predictable performance.