OpenAI: gpt-oss-120bopenai
OpenAI: gpt-oss-120b: $0.15/1M input, $0.60/1M output, 131K context, CPS grade A. 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...
API Pricing (per 1M tokens)
| Input | $0.15 |
| Output | $0.60 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.26 |
Specs & Performance
| Context Length | 131K |
| Max Output | 66K |
| Intelligence | 12 |
| Coding | 30 |
| Math | 93 |
| Speed | 200 tok/s |
| TTFT | 0.49s |
| CPS Grade | A |
| Input / Output Modalities | text → text |
More from openai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the OpenAI: gpt-oss-120b API cost?
OpenAI: gpt-oss-120b costs $0.15/1M input tokens and $0.60/1M output tokens. Blended cost at a 3:1 ratio is about $0.26/1M tokens.
What is the context window of OpenAI: gpt-oss-120b?
OpenAI: gpt-oss-120b supports a 131K token context window with up to 66K output tokens.
Is OpenAI: gpt-oss-120b worth it?
OpenAI: gpt-oss-120b has a CPS grade of A (score 68), intelligence index 12, coding index 30. Use the compare page to benchmark against rivals.