OpenAI: gpt-oss-120b
openai/gpt-oss-120b
110th smartest of 182Cheaper than 97% of paidReasoningToolsJSON
Intelligence
23.8
110th of 182
Design Elo
1029
Data Viz
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.037
10th cheapest
Context
131K
131K max out
How it compares
Smarter than40%
of all ranked models
Cheaper than97%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis67th percentile
Intelligence Index
23.8
Coding Index
30.4
GPQA Diamond
78%
Humanity's Last Exam
19%
SciCode
39%
Tau²-Bench (agentic)
66%
Design Arena · Elo102 tournaments
Data Viz
1029
Website
992
3D
958
Providers & pricing (19)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| CoreWeavefp4 | $0.030 | $0.170 | 131K | 95.2% |
| DeepInfrabf16 | $0.037 | $0.170 | 131K | 99.7% |
| Novitafp4 | $0.050 | $0.250 | 131K | 99.9% |
| SiliconFlowfp8 | $0.050 | $0.450 | 131K | 100% |
| Mancer 2fp8 | $0.060 | $0.500 | 131K | 99.4% |
| DigitalOcean | $0.070 | $0.490 | 128K | 99.9% |
| $0.090 | $0.360 | 131K | 99.9% | |
| BaseTenfp4 | $0.100 | $0.500 | 128K | 100% |
| Parasailfp4 | $0.100 | $0.750 | 131K | 95.9% |
| SambaNova | $0.140 | $0.950 | 131K | 91% |
| Amazon Bedrock | $0.150 | $0.600 | 131K | 100% |
| DeepInfrabf16 | $0.150 | $0.600 | 131K | 99.7% |
| Together | $0.150 | $0.600 | 131K | 100% |
| Nebiusfp4 | $0.150 | $0.600 | 131K | 99.8% |
| Amazon Bedrock | $0.150 | $0.600 | 131K | — |
| Phala | $0.150 | $0.600 | 131K | 98.5% |
| Groq | $0.150 | $0.600 | 131K | 100% |
| Mara | $0.150 | $0.750 | 131K | 95.6% |
| Cerebrasfp16 | $0.350 | $0.750 | 131K | 100% |
Specifications
Context window131K
Max output131K
Knowledge cutoffJun 2024
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsopenai/gpt-oss-120b ↗
gpt-oss-120b FAQ
How much does gpt-oss-120b cost?
gpt-oss-120b costs $0.037 per million input tokens and $0.170 per million output tokens via OpenRouter, making it 10th cheapest of 332 paid models.
How smart is gpt-oss-120b?
gpt-oss-120b scores 23.8 on the Artificial Analysis Intelligence Index, ranking 110th of 182 benchmarked models, with a GPQA Diamond score of 78%.
What is gpt-oss-120b's context window?
gpt-oss-120b supports a 131K-token context window and can output up to 131K tokens. It accepts text input.