# gpt-oss-120b — price & specs

Source: https://modelbank.ai/models/gpt-oss-120b · updated 2026-11-12 · ModelBank

| Field | Value |
|---|---|
| Vendor | OpenAI |
| Input price | $0.15 / 1M tokens |
| Output price | $0.6 / 1M tokens |
| Cached input | $0.075 / 1M tokens |
| Context window | 131,072 tokens |
| Max output | 65,536 tokens |
| Input modalities | text |
| Reasoning / tool use | yes / yes |
| Intelligence / coding index | 3.8 / 30.4 |
| Released | 2025-08-05 |
| Retirement date | none announced |

## About

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...

## Price history

- 2026-09-24: $0.15 in / $0.6 out
- 2026-09-29: $0.037 in / $0.17 out
- 2026-10-13: $0.15 in / $0.6 out
- 2026-10-14: $0.037 in / $0.17 out
- 2026-10-15: $0.15 in / $0.6 out
- 2026-11-01: $0.02 in / $0.075 out
- 2026-11-02: $0.15 in / $0.6 out
- 2026-11-06: $0.01 in / $0.037 out
- 2026-11-06: $0.023 in / $0.087 out
- 2026-11-07: $0.012 in / $0.044 out
- 2026-11-07: $0.018 in / $0.067 out
- 2026-11-09: $0.15 in / $0.6 out

## Cheaper alternatives with similar intelligence

- [GLM 5.3 Flash](https://modelbank.ai/models/glm-5.3-flash): $0.0399 / $0.0784, intelligence 27.8
- [Granite 4.2 8B](https://modelbank.ai/models/granite-4.2-8b): $0.06 / $0.15, intelligence 5.1
- [Nemotron 3.5 Lightning](https://modelbank.ai/models/nemotron-3.5-lightning): $0.07 / $0.2, intelligence 5.5
- [DeepSeek V4.1 Flash 1017](https://modelbank.ai/models/deepseek-v4.1-flash-1017): $0.098 / $0.29, intelligence 28.6
- [MiMo-V2.6-Flash](https://modelbank.ai/models/mimo-v2.6-flash): $0.14 / $0.28, intelligence 26.7

JSON: https://modelbank.ai/api/v1/models/gpt-oss-120b