Install

gpt-oss-120b as a coding agent in your terminal

gpt-oss-120b by OpenAI, one of 250+ models you can use in Darce, the open source AI coding agent you can undo.

Modelgpt-oss-120b
VendorOpenAI
Model idopenai/gpt-oss-120b
Context window131k tokens
Price per 1M tokens$0.037 input · $0.17 output (OpenRouter)
Can dotool calling · reasoning
CategoryOpen weights and budget

Strengths

OpenAI's open-weight model. Very inexpensive, good for simple tasks and experiments.

OpenRouter's description:

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...

Use gpt-oss-120b as a coding agent in your terminal

Start Darce in your project with gpt-oss-120b:

npm install -g darce-cli
darce --model openai/gpt-oss-120b

Already in a session? Type /model openai/gpt-oss-120b, or open the picker with Ctrl+P. Darce then reads your code, edits files and runs commands with gpt-oss-120b; risky commands ask first, and /undo reverses any change, including what shell commands did. No account yet? npx darce-cli lets you try it free. Which plan includes which models is on the pricing page.

Make it your default or a gear

In ~/.darcerc, set it as the starting model or add it to the gears you move between with Shift+↑ / Shift+↓ (see configuration):

{
  "router": { "default": "openai/gpt-oss-120b" },
  "gears": ["qwen/qwen3-coder", "openai/gpt-oss-120b"]
}

Compare it on your own code

Benchmarks rarely match your repository. Race gpt-oss-120b against two other models on a real task and keep the best diff:

/derby --models openai/gpt-oss-120b,openai/gpt-6.1-sol,openai/gpt-6-sol fix the failing test

Read more about /derby and /swarm.

Related models

  • GPT-6.1 Sol (OpenAI): 1.05M tokens, $2.00 / $10.00 per 1M tokens
  • GPT-6 Sol (OpenAI): 1.05M tokens, $2.00 / $10.00 per 1M tokens
  • GPT-6 Luna (OpenAI): 1.05M tokens, $0.10 / $0.50 per 1M tokens
  • GPT-6 Astra (OpenAI): 1.05M tokens, $10.00 / $50.00 per 1M tokens
  • Gemma 4 31B (Google): 262k tokens, $0.090 / $0.34 per 1M tokens
  • Qwen3 Coder 30B A3B Instruct (Qwen (Alibaba)): 262k tokens, $0.070 / $0.28 per 1M tokens
  • DeepSeek V3.2 (DeepSeek): 164k tokens, $0.26 / $0.80 per 1M tokens
  • Kimi K2.6 (Moonshot AI): 262k tokens, $0.47 / $2.45 per 1M tokens

All models · Getting started · Claude Code alternative

Model data from OpenRouter, refreshed daily. Prices are OpenRouter's list rates and show relative cost; your Darce allowance is used in proportion to them.