Primary use stated or inferred cautiously from official documentation.
O
OPENAI / gpt-oss-120b
gpt‑oss‑120b
Reasoning model with open weights for local or private execution; fits on one H100 GPU according to OpenAI.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gpt-oss-120b |
|---|---|
| Model type | Text and reasoning · Code |
| Access model | Open weights |
| License | Apache 2.0 |
| Deployment | Local, private cloud, or provider |
| Release | AGO 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text |
| Exit | Text |
| Context window | 131,072 tokens |
| maximum output | Not published |
| Reasoning | Adjustable reasoning |
| Published tools | |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Downloadable weights |
| Verified platforms | Hugging Face · Proveedores de inferencia |
Private reasoning, customization, and deployments that require infrastructure control.
Requires your own hardware and operations; performance depends on the runtime and quantization.
03 / CAPABILITIES
What it can do
Orientation
Private reasoning, customization, and deployments that require infrastructure control.
Context
131,072 tokens · Not published
Tools and integration
Not published
Access
Weight download
Input modalities
Text
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Evaluaciones gpt‑oss | Published o4-mini level | General reasoning | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
gpt‑oss‑120b
Version added to Inferama's verified catalog.
07 / SOURCES