TokenCosts AI.iov1.0
Back to Models Directory
OpenAIgpt-oss-120b

OpenAI: gpt-oss-120b API Pricing

Official PricingCall via OpenRouter

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B ...

Base Input Price$0.15/ 1M tokens
Base Output Price$0.60/ 1M tokens
Prompt Cache Read$0.075-50% discount
Batch API Rate-80.27%24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
OpenAI Direct$0.15$0.60SupportedConnect
OpenRouter$0.15$0.60SupportedConnect

Head-to-Head Comparisons for OpenAI: gpt-oss-120b

OpenAI: gpt-oss-120b vs OpenAI: GPT-6.1 Sol$0.15/M vs $2/M
OpenAI: gpt-oss-120b vs GPT-4o (Omni)$0.15/M vs $2.5/M
OpenAI: gpt-oss-120b vs Claude 3.5 Sonnet$0.15/M vs $3/M
OpenAI: gpt-oss-120b vs DeepSeek-V3 (deepseek-chat)$0.15/M vs $0.27/M