ModelsGPT-OSS-120B

GPT-OSS-120B

by OpenAI

Cost-effective

Best value for production workloads

Pricing
Input
Self-hosted
per 1M tokens
Output
Self-hosted
per 1M tokens
Cached
N/A
per 1M tokens
Note: Released Aug 2025. OpenAI's first open-weight model since GPT-2
Context & Output
Context Window128K tokens
Max Output32K tokens
Latency
Fast
Capabilities
Multimodal
Streaming
Function Calling
Prompt Caching
Key Strengths
What makes this model stand out
Matches o4-mini
117B total (5.1B active)
Open weights
Similar Models in Cost-effective Tier
Other models with similar pricing and performance characteristics
Amazon Nova 2 Lite
Amazon
Input:TBD/M
Context:1M tokens
View Details
Amazon Nova 2 Sonic
Amazon
Input:TBD/M
Context:1M tokens
View Details
DeepSeek V3.1
DeepSeek
Input:$0.56/M
Context:128K tokens
View Details
Compare all models →