Process massive datasets with gpt-oss-120b, featuring an expansive 131K context window for long-document analysis. This model delivers cost-effective pricing at $0.15/1M input and $0.60/1M output tokens, native tool calling support. Access gpt-oss-120b via the Weights & Biases API with up to 131K output tokens.
Tokens
Tokens
Tokens
gpt-oss-120b by Weights & Biases costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.