OpenAI: gpt-oss-120b
Analysis Summary
OpenAI: gpt-oss-120b sits in the Specialist tier on our leaderboard, ranked #125 of 556 published models on overall intelligence. At $0.039 input and $0.180 output per 1M tokens, it is among the most expensive on the market. It offers a standard large context window and supports tool use, function calling, and reasoning.
Editorial notes
OpenAI gpt-oss-120b is a compact open-weights model with strong math performance and tool use support, but limited coding and agentic capability keep it suited to lighter general tasks at its very competitive $0.04/1M input price.
Assessed May 14, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: gpt-oss-120b stack up?
Compare side-by-side with other specialist models.
Model Information
| OpenRouter ID |
openai/gpt-oss-120b
|
| Provider | openai |
| Release Date | August 5, 2025 |
| Context Length | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.04 | $0.000039 |
| Output | $0.18 | $0.000180 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
