GPT OSS 120B
gpt-oss-120b
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI.
Intelligence
Medium
Speed
Medium
Price
$0.05 • $0.25
Input • Output
Input
Text
Output
Text
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.
131000 context window
100000 max output tokens
knowledge cutoff
Modalities
Text
Input and output
Image
Not supported
Audio
Not supported
Video
Not supported
Endpoints
Chat Completions
v1/chat/completions
Responses
v1/responses
Realtime
v1/realtime
Assistants
v1/assistants
Batch
v1/batch
Fine-tuning
v1/fine-tuning
Embeddings
v1/embeddings
Image generation
v1/images/generations
Videos
v1/videos
Image edit
v1/images/edits
Speech generation
v1/audio/speech
Transcription
v1/audio/transcriptions
Translation
v1/audio/translations
Moderation
v1/moderations
Completions (legacy)
v1/completions
Features
Streaming
Supported
Function calling
Not supported
Structured outputs
Not supported
Fine-tuning
Not supported
Distillation
Not supported
Tools
Tools supported by this model when using the Responses API.
Web search
Not supported
File search
Not supported
Image generation
Not supported
Code interpreter
Not supported
Computer use
Not supported
MCP
Not supported