OpenAI: gpt-oss-120b

Text input Text output Free Option
Author's Description

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Key Specifications
Cost
$$$
Context
131K
Parameters
120B
Released
Aug 05, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Frequency Penalty Top P Reasoning Temperature Stop Presence Penalty Include Reasoning Tool Choice Max Tokens Logit Bias
Features

This model supports the following features:

Tools Reasoning
Performance Summary

The OpenAI gpt-oss-120b model, an open-weight 117B-parameter Mixture-of-Experts (MoE) model, demonstrates a balanced performance profile across various benchmarks. It exhibits competitive response times, ranking in the 54th percentile, and offers cost-effective solutions, placing in the 62nd percentile for pricing. Notably, the model boasts exceptional reliability with a 97% success rate, indicating consistent and stable operation. In terms of specific performance, gpt-oss-120b shows outstanding capabilities in Coding, achieving perfect accuracy in one benchmark and strong 93% accuracy in another, often performing among the fastest models in this category. It also excels in General Knowledge (99.5% accuracy), Email Classification (99.0% accuracy), and Reasoning (96.0% accuracy). The model demonstrates strong performance in handling hallucinations, with a 98.0% accuracy, and solid mathematical abilities (94.0% accuracy). A key strength is its ability to achieve perfect accuracy in coding while maintaining competitive speed. However, its performance in Instruction Following (46.0% accuracy) and Ethics (93.8% accuracy, 23rd percentile) suggests areas for potential improvement, as these scores are comparatively lower. The model's configurable reasoning depth and native tool use are significant features for production use cases.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.15
Completion $0.6
Input Cache Read $0.014

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Fireworks
Fireworks | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
Groq
Groq | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
Cerebras
Cerebras | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
BaseTen
BaseTen | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Parasail
Parasail | openai/gpt-oss-120b 131K $0.1 / 1M tokens $0.75 / 1M tokens
Together
Together | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
Novita
Novita | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Nebius
Nebius | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
DeepInfra
DeepInfra | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
AtlasCloud
AtlasCloud | openai/gpt-oss-120b 131K $0.1 / 1M tokens $0.4 / 1M tokens
Chutes
Chutes | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Crusoe
Crusoe | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Phala
Phala | openai/gpt-oss-120b 131K $0.1 / 1M tokens $0.49 / 1M tokens
NCompass
NCompass | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
GMICloud
GMICloud | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
GMICloud
GMICloud | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
WandB
WandB | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
SambaNova
SambaNova | openai/gpt-oss-120b 131K $0.14 / 1M tokens $0.95 / 1M tokens
WandB
WandB | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
InferenceNet
InferenceNet | openai/gpt-oss-120b 100K $0.039 / 1M tokens $0.19 / 1M tokens
Google
Google | openai/gpt-oss-120b 131K $0.09 / 1M tokens $0.36 / 1M tokens
BaseTen
BaseTen | openai/gpt-oss-120b 128K $0.1 / 1M tokens $0.5 / 1M tokens
Chutes
Chutes | openai/gpt-oss-120b 131K $0.09 / 1M tokens $0.36 / 1M tokens
SiliconFlow
SiliconFlow | openai/gpt-oss-120b 131K $0.05 / 1M tokens $0.45 / 1M tokens
DeepInfra
DeepInfra | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
Novita
Novita | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Crusoe
Crusoe | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Amazon Bedrock
Amazon Bedrock | openai/gpt-oss-120b 131K $0.15 / 1M tokens $0.6 / 1M tokens
Clarifai
Clarifai | openai/gpt-oss-120b 131K $0.09 / 1M tokens $0.36 / 1M tokens
BytePlus
BytePlus | openai/gpt-oss-120b 128K $0.039 / 1M tokens $0.19 / 1M tokens
Mara
Mara | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Novita
Novita | openai/gpt-oss-120b 131K $0.05 / 1M tokens $0.25 / 1M tokens
Cerebras
Cerebras | openai/gpt-oss-120b 131K $0.35 / 1M tokens $0.75 / 1M tokens
Io Net
Io Net | openai/gpt-oss-120b 131K $0.09 / 1M tokens $0.351 / 1M tokens
DeepInfra
DeepInfra | openai/gpt-oss-120b 131K $0.039 / 1M tokens $0.19 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai