OpenAI Model Pricing & Calculator Proprietary Cloud API

OpenAI: gpt-oss-120b (batch) API Cost Calculator

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 parameters per forward pass and is optimized...

Interactive Monthly Spend Estimator

Adjust sliders to calculate your daily and monthly bill for OpenAI: gpt-oss-120b (batch).

Estimated Daily API Cost $0.00
Estimated Monthly API Cost (30 days) $0.00
24/7 2x NVIDIA H100 (160GB VRAM) (Open-Weight Alternative) $3,873.60/mo

Official Token Pricing & Specs

Model ID openai/gpt-oss-120b:batch
Provider OpenAI
Weight Availability Proprietary Cloud API (Closed Weights)
Input Price (per 1M tokens) $0.0296
Output Price (per 1M tokens) $0.136
Max Context Window 131,072 tokens
Open-Weight Eq. VRAM (~120B Class) ~78.0 GB Q4 Equivalent Guide โ†’
API vs. GPU Daily Break-Even ~2099.5M tokens/day
Deploy on RunPod (From $0.20/hr) Rent GPUs on Vast.ai (Save up to 70%)
Best for Serverless & Dedicated AI GPUs

Stop Overpaying for High-Volume AI Inference

Spending heavily on OpenAI: gpt-oss-120b (batch) API calls? Benchmark open-weight alternatives (Llama 4, Qwen 3, DeepSeek V3/R1) on dedicated H100, A100, or RTX 4090 GPUs from $0.20/hr.

Deploy on RunPod (From $0.20/hr) โ†’

Compare OpenAI: gpt-oss-120b (batch) With Other Popular Models