Model Library
OpenAIReleased August 5, 2025gpt-oss-120b (high)
OpenAI · Released August 5, 2025
Intelligence score
24
At a glance
- Intelligence
- 24
- Speed
- 314.1tokens/sec
- Latency
- 870mstime to first token
- Input price
- $0.15per 1M tokens
- Output price
- $0.60per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 117billions
Summary
Comparison summary
gpt-oss-120b (high) scores 24 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). gpt-oss-120b (high) generates output at 314.1 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 88.2 t/s). gpt-oss-120b (high) costs $0.15 per 1M input tokens (very competitive, median: $0.40) and $0.60 per 1M output tokens (better than average, median: $0.84), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | gpt-oss-120b (high) |
|---|---|
| Provider | OpenAI |
| Release date | August 5, 2025 |
| Intelligence score | 24 |
| Speed | 314.1 tokens/sec |
| Latency (TTFT) | 0.87s |
| Input price | $0.15 / 1M tokens |
| Output price | $0.60 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 117B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: gpt-oss-120b |
Pricing
Token prices
Price per 1M tokens
gpt-oss-120b (high), as listed in the catalog record
- Input$0.15
- Output$0.60
| Token type | Price per 1M |
|---|---|
| Input | $0.15 |
| Output | $0.60 |
Model Intelligence legacy profile: gpt-oss-120b
FAQ · 22
Frequently asked questions
gpt-oss-120b (high) was released on August 5, 2025.
gpt-oss-120b (high) was created by OpenAI.
gpt-oss-120b (high) scores 24 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
gpt-oss-120b (high) generates output at 314.1 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 88.2 t/s).
gpt-oss-120b (high) has a time to first token (TTFT) of 0.87s (based on the median across providers serving the model), which is very competitive compared to other open weight models of similar size (median: 1.52s).
gpt-oss-120b (high) costs $0.15 per 1M input tokens (very competitive, median: $0.40) and $0.60 per 1M output tokens (better than average, median: $0.84), based on the median across providers serving the model.
gpt-oss-120b (high) costs $0.15 per 1M input tokens and $0.60 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.20 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, gpt-oss-120b (high) generated 87M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 59M).
Yes, gpt-oss-120b (high) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
gpt-oss-120b (high) supports text input.
gpt-oss-120b (high) supports text output.
No, gpt-oss-120b (high) does not support image input. It can only process text.
No, gpt-oss-120b (high) is not multimodal. It only supports text input.
gpt-oss-120b (high) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, gpt-oss-120b (high) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
gpt-oss-120b (high) has 117 billion parameters (5.1 billion active).
gpt-oss-120b (high) is a Mixture of Experts (MoE) model with 117 billion total parameters, but only 5.1 billion active parameters are used during inference.
gpt-oss-120b (high) is released under the Apache 2.0 license. This license allows commercial use.
gpt-oss-120b (high) achieves a score of 24 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
gpt-oss-120b (high) has a knowledge cutoff of May 2024. The model's training data includes information up to this date.
Yes, gpt-oss-120b (high) is available via API through 23 providers.
gpt-oss-120b (high) is available through 23 API providers.