openai

OpenAI: gpt-oss-120b

This AI model, developed by OpenAI, is called gpt-oss-120b. It processes text input and can handle contexts of up to 131072 tokens. The model supports the use of tools and demonstrates reasoning capabilities. If you're looking for an AI that balances performance with cost, consider this option. With a blended benchmark score of 40.1 across three independent benchmarks, it offers decent results without breaking the bank. At $0.037 per million input tokens and $0.17 per million output tokens, its price point is relatively affordable.

Open weights 117B parameters, about 65.4 GiB at Q4_K_M: fits comfortably on 0 of 17 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
91/100
price + capability + benchmarks
Input Price
$0.04
per 1M tokens · checked 2026-09-10
Output Price
$0.17
per 1M tokens · checked 2026-09-10
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 40.1 across 3 benchmarks, last refreshed 2026-09-10. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 41.8
AI Index broad capability composite 20.4
EQ-Bench emotional understanding in dialogue 53.4
Model ID
openai/gpt-oss-120b
Vendor
openai
Released
August 2025
Tokenizer
GPT
Input Modalities
text
Output Modalities
text
Max Output
117,964 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.04/M input and $0.17/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.03
A month of a busy support chatbot 5M in / 2M out $0.53

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-08-23 $0.04 $0.17 131,072
2026-08-12 $0.03 $0.17 131,072
2026-07-17 $0.04 $0.17 131,072

Similar models

Quick answers

How much does OpenAI: gpt-oss-120b cost?
$0.04 per million input tokens and $0.17 per million output tokens.
What is OpenAI: gpt-oss-120b's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does OpenAI: gpt-oss-120b support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can OpenAI: gpt-oss-120b process images?
No, it is text-only on the input side.