modelgrep
O

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

66th smartest of 178Cheaper than 97% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
33.3
66th of 178
Design Elo
1062
Game Dev
Speed
547
4th fastest
Latency
177ms
first token
Input price
$0.039
10th cheapest
Context
131K

How it compares

Smarter than63%
of all ranked models
Faster than99%
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 · via OpenRouter
Artificial Analysis61th percentile
Intelligence Index
33.3
Coding Index
28.6
Agentic Index
37.9
GPQA Diamond
78%
Humanity's Last Exam
19%
SciCode
39%
Tau²-Bench (agentic)
66%
Design Arena · Elo2,487 tournaments
Game Dev
1062
Data Viz
1044
codecategories
1015
Website
1013
3D
981
UI Component
981

Providers & pricing (19)

ProviderIn $/MOut $/MUptime
DekaLLMbf16$0.039$0.18099.5%
DeepInfrabf16$0.039$0.190100%
WandBfp4$0.040$0.140100%
Novitafp4$0.050$0.250100%
SiliconFlowfp8$0.050$0.45092.9%
DigitalOcean$0.075$0.52599.8%
Google$0.090$0.36099.8%
BaseTenfp4$0.100$0.500100%
Parasailfp4$0.100$0.750100%
SambaNova$0.140$0.95095.2%
Amazon Bedrock$0.150$0.600100%
Phala$0.150$0.60070.8%
Amazon Bedrock$0.150$0.600
Together$0.150$0.60097%
Groq$0.150$0.600100%
Nebiusfp4$0.150$0.600100%
DeepInfrabf16$0.150$0.60098%
Mara$0.150$0.75071.2%
Cerebrasfp16$0.350$0.750100%

Specifications

Context window131K
Max output
Knowledge cutoffJun 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

gpt-oss-120b FAQ

How much does gpt-oss-120b cost?

gpt-oss-120b costs $0.039 per million input tokens and $0.180 per million output tokens via OpenRouter, making it 10th cheapest of 298 paid models.

How smart is gpt-oss-120b?

gpt-oss-120b scores 33.3 on the Artificial Analysis Intelligence Index, ranking 66th of 178 benchmarked models, with a GPQA Diamond score of 78%.

How fast is gpt-oss-120b?

gpt-oss-120b generates around 547 tokens per second with 177ms time-to-first-token (p50), the 4th fastest tracked model.

What is gpt-oss-120b's context window?

gpt-oss-120b supports a 131K-token context window. It accepts text input.

Compare head-to-head