- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- openai
- Family
- gpt-oss
- Task
- text-generation
- Hugging Face
- openai/gpt-oss-120b
- OpenRouter
- openai/gpt-oss-120b
- Also known as
- gpt-oss-120b, gpt oss 120b, gptoss120b
02Registry facts
- LicenceFACT
apache-2.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
116.8B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
5,117,998
- FreshRetrieved 19 Sep 2026
- LikesFACT
5,267
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
5117998
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · DekaLLMFACT
131072
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · CoreWeaveFACT
131072
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · AkashMLFACT
131072
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
5267
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
apache-2.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
116829156672
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · DekaLLMFACT
0.1800
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · CoreWeaveFACT
0.1700
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · AkashMLFACT
0.1700
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · DekaLLMFACT
0.0300
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · CoreWeaveFACT
0.0300
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · AkashMLFACT
0.0300
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · awsFACT
aws
The source document changed after this was recorded; it is queued for re-checking.
- Verification may be outdatedRetrieved 19 Sep 2026
- last modifiedFACT
2025-08-26T17:25:03.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 116.8B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 233.66 GB | 285.99 GB |
| fp8 | 116.83 GB | 151.64 GB |
| int4 | 58.41 GB | 84.46 GB |
What this estimate assumes
- Weights: 116.8B parameters × 2 bytes per parameter (fp16) = 233.66 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 37.3 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.03
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.16999999999999998
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| AkashML | 131,072 |
| CoreWeave | 131,072 |
| DekaLLM | 131,072 |
| DeepInfra | 131,072 |
| Crusoe | 131,072 |
| Novita | 131,072 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
Models at a glance - Amazon Bedrock
https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html
AgeingRetrieved 19 Sep 2026sha256:4c3b2b5762261 record
- 02–10Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — openai/gpt-oss-120b
https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints
AgeingRetrieved 19 Sep 2026sha256:9465b7e9ac259 records · · · · · · · ·
- 11–17Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — openai/gpt-oss-120b
https://huggingface.co/api/models/openai/gpt-oss-120b
Verification may be outdatedRetrieved 19 Sep 2026sha256:7545370c28107 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.