All AI models · LLM benchmarks · Methodology

OpenAI

GPT OSS 120B

Open GPT reasoning model for self-hosted agents and controllable deployments

Model facts

Context window
131K tokens
Maximum output
33K tokens
Cheapest paid input
$0.039 per 1M tokens
Cheapest paid output
$0.1 per 1M tokens
Open weights
yes
Providers
85

Capabilities and modalities

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

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.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
high24.130.493.4151.6
low14.921.266.7156.1

Observed price history

  • 2026-08-24: $0.039 input / $0.1 output per 1M tokens

API providers