OpenAI: gpt-oss-120b

openai/gpt-oss-120b

PaidTool callingReasoning
View on OpenRouter ↗

Price Published

Input
$0.04
per million tokens
Output
$0.17
per million tokens

Optional features and fallback routes can cost extra. Confirm current terms with the provider.

Specifications Published

Context window
131,072 tokens
Max output
117,964 tokens
Tool calling
Supported
Vision input
Not listed
Reasoning
Supported
Knowledge cutoff
Jun 30, 2024
Listed since
Aug 5, 2025

Measured by the Club Signed cheapoS reports

Not yet observed No signed request reports for this exact route yet. Missing reports aren't a failure or a zero.

How we measure · Reports come from cheapoS members who share model details.

Benchmarks Artificial Analysis via OpenRouter

Intelligence index
11.6
Coding index
30.4
Agentic index
3.7

Scores from Artificial Analysis, as distributed in the OpenRouter catalog. They measure test suites, not request reliability on real work.

Try it

  1. Get an OpenRouter API key. Create one here. Other free tiers are compared on Providers.
  2. Add it to cheapoS. Open Models → Open OmniRoute, add OpenRouter with your key, then refresh models. Get cheapoS
  3. Pick this model. Use the ID openai/gpt-oss-120b as a worker or reviewer, and start with a small task you can check.

About this model OpenRouter 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...

Similar-priced alternatives with tool calling

Catalog data from the OpenRouter model catalog, retrieved Sep 29, 2026, 12:37 PM UTC. A listing isn't a live availability check.