gpt-oss-120b
OPENAI Developer Architecture Profile
Intelligence (ELO)1049Chatbot Arena Verified
Max Context Limit131,072Max Out: 117,964 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.21🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Reasoning
- 🧠 Extended Test-Time Reasoning
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...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.04 / 1M
Output Tokens (Completion)$0.17 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine Matchupgpt-oss-120b vs NVIDIA: Nemotron 3 Ultra (free)VS Engine Matchupgpt-oss-120b vs Mistral: Voxtral Small 24B 2507VS Engine Matchupgpt-oss-120b vs Space Bunny AlphaVS Engine Matchupgpt-oss-120b vs Auto RouterVS Engine Matchupgpt-oss-120b vs Meta: Muse Spark 1.3 ContributorVS Engine Matchupgpt-oss-120b vs Tencent: Hy-MT2-7B