GPT OSS 20B
gpt-oss-20b
GPT OSS 20B is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
GPT OSS 20B is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Intelligence
Medium
Speed
Medium
Price
$0.03 • $0.14
Input • Output
Input
Text
Output
Text
GPT OSS 20B uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
4096 context window
2048 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