Process massive datasets with Hermes 4 Large (Thinking), featuring an expansive 128K context window for long-document analysis. This model delivers cost-effective pricing at $0.30/1M input and $1.20/1M output tokens, open weights architecture. Access Hermes 4 Large (Thinking) via the NanoGPT API with up to 8K output tokens.
Tokens
Tokens
Tokens
Hermes 4 Large (Thinking) by NanoGPT costs $0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached reads cost $0.15 per 1M tokens.