openai

OpenAI: gpt-oss-120b (free)

by openai

OpenRouter
Tools Reasoning Long Context

About

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Specifications

Context Length 131K
Max Output Tokens 131K
Modality text->text
Input text
Output text
Supported Parameters include_reasoning, max_tokens, reasoning, seed, stop, temperature, tool_choice, tools
Content Moderation Yes

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...
Model 1h 6h 24h 7d 30d
OpenAI: gpt-oss-120b (free) - - - - 100.0%

Availability

Available 41 of 41 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

FebMar
ModelDays181920212223242526272812345678910111213141516171819
OpenAI: gpt-oss-120b (free)30

Similar Models

nvidia NVIDIA: Nemotron Nano 9B V2 (free) 128K arcee-ai Arcee AI: Trinity Mini (free) 131K nvidia NVIDIA: Nemotron 3 Nano 30B A3B (free) 256K nvidia NVIDIA: Nemotron 3 Super (free) 262K stepfun StepFun: Step 3.5 Flash (free) 256K

More from Openai

openai OpenAI: gpt-oss-20b (free) 131K

Frequently Asked Questions

Is OpenAI: gpt-oss-120b (free) free to use?

Yes, OpenAI: gpt-oss-120b (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for OpenAI: gpt-oss-120b (free)?

OpenAI: gpt-oss-120b (free) supports a context window of 131K tokens (131,072 tokens).

What is the maximum output length for OpenAI: gpt-oss-120b (free)?

OpenAI: gpt-oss-120b (free) can generate up to 131K tokens (131,072 tokens) per response.

Does OpenAI: gpt-oss-120b (free) support function calling (tools)?

Yes, OpenAI: gpt-oss-120b (free) supports function calling / tool use, enabling it to interact with external APIs and services.

Does OpenAI: gpt-oss-120b (free) support reasoning?

Yes, OpenAI: gpt-oss-120b (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.