| Created | June 11, 2026 |
| Updated | June 16, 2026 |
| Confidence | 95% |
| url | https://fireworks.ai/ |
| why_us | Top-tier inference provider for AI agent builder teams — Cursor, Notion, and Vercel v0 all use Fireworks in production for their agent/copilot features. Reduced Notion AI latency from 2s to 350ms. Multi-LoRA supports personalized per-user agent fine-tuning. |
| has_api | true |
| has_mcp | false |
| pricing | paid |
| added_at | 2026-06-11 |
| added_by | user |
| curated_at | 2026-06-11 |
| curated_by | kb-curator-agent |
| curation_run | 1 |
| main_use_case | Run, fine-tune, and scale open-source LLM inference with industry-leading throughput and latency, optimized for agentic systems, code assistance, and enterprise RAG. |
| relevance_tier | useful |
| community_notes | Created by PyTorch founders; Jensen Huang called it the TSMC of AI Factories at NVIDIA GTC 2026. Serverless 2.0 allows reliability/speed control without reserved capacity. Cursor chose Fireworks over open-source engines for production-grade RL inference. |
