OpenAI model product
GPT-OSS-120B
8B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
Updated Aug 12, 2026. Default version: GPT OSS 120B High
LLMBoard score44.0GPT OSS 120B High
Coverage100%7 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
GPT-OSS-120B Specifications
Technical details for the model's default version.
- Version
- GPT OSS 120B High
- Released
- Aug 5, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 116.8B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
GPT-OSS-120B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-OSS-120B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
GPT-OSS-120B Runtime Performance
Provider-specific output speed and catalog latency for GPT OSS 120B High. Runtime does not affect the capability score.
| OpenAI | 100 tok/s | 6.5 s | 131.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-OSS-120B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-OSS-120B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT OSS 120B | N/A | 116.8B | 131.1K | 32.8K | Yes | Apache 2.0 | |
| GPT OSS 120B High | 44.0 | 116.8B | 131.1K | 131.1K | No | Apache 2.0 |
What is GPT-OSS-120B?
Key information about GPT-OSS-120B and its available data.
8B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. 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. It achieves near-parity with OpenAI o4-mini on core reasoning benchmarks. 8B parameters.
Data as of 2026-08-11.
GPT-OSS-120B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-OSS-120B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5-Codex
OpenAI
OP
GPT-5-mini
OpenAI
OP
o4 mini
OpenAI
OP
GPT-5.3
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-5.4-nano
OpenAI
FAQ
Common questions about GPT-OSS-120B.
When was GPT-OSS-120B released?
GPT-OSS-120B's default version was released on Aug 5, 2025.
How much does GPT-OSS-120B cost?
No official standard PAYG price is currently available for GPT-OSS-120B.
Who created GPT-OSS-120B?
GPT-OSS-120B was created by OpenAI.
What is the context window for GPT-OSS-120B?
The default version has a 131.1K token context window.
Is GPT-OSS-120B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-OSS-120B?
No provider offering is currently linked to the default version.
What models should I compare GPT-OSS-120B with?
Nearby ranked alternatives include Nemotron 3 Super, Sarvam 105B, DeepSeek-R1.