gpt-oss-120b
Provider：OpenAI
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...
Key specs
- Context：131.1K
- Max output：118K
- Tokenizer：GPT
- Released：2025-08-05
Token pricing
- Input price：$0.037 / 1M tokens
- Output price：$0.170 / 1M tokens
- Blended price：$0.070 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Math proofs, logical reasoning, multi-step planning — ideal for research and financial analysis.（≈ $0.0014/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Low blended price: budget-friendly for fleet-scale deployment.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of gpt-oss-120b? Input price $0.037 / 1M tokens, output price $0.170 / 1M tokens, blended about $0.070 / 1M tokens. Refer to OpenAI’s official page for the exact rate.
- What context window does gpt-oss-120b support? Context window is 131.1K, max output about 118K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is gpt-oss-120b best for? Based on its capability and pricing, gpt-oss-120b fits best: Deep Reasoning & Analysis. See the Use Cases section for details and cost estimates.
- What input/output modalities does gpt-oss-120b support? Supports Text modality.
- Is gpt-oss-120b a free model? gpt-oss-120b is billed per token, not a free model.
- Which provider offers gpt-oss-120b? gpt-oss-120b is offered by OpenAI.
More models from OpenAI
Full info：gpt-oss-120b