All AI models · LLM benchmarks · Methodology

OpenAI

GPT 120B

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Model facts

Context window
128K tokens
Maximum output
128K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.5 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 72.5 GiB, Q8_0 126.9 GiB, F16 228.9 GiB working memory.

Parameters
116.8 billion
Architecture
gptoss
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $0.1 input / $0.5 output per 1M tokens

API providers

  • Baseten (OpenAI) — model id openai/gpt-oss-120b; $0.1 input / $0.5 output per 1M tokens; provider documentation