LLM Performance

Writer's API/LLMs output speed is based on words generated. We are proud to have one of best performance matrixes across industry leaders:

Writer

• Enterprise API: ~65ms per generated word
• Team/Free Trial: ~200ms per generated word

OpenAI

• OpenAI GPT-3.5: ~73ms per generated token
• OpenAI GPT-4: ~196ms per generated token