low · medium · high
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / OPENAI
gpt-oss-120b
verified model reference.
OpenAI open-weight reasoning model for self-hosted deployment with function calling and agentic capabilities.
131,072context tokens
131,072max output
2026-10-07last verified
PRIMARY-SOURCE VERIFIED
gpt-oss-120b at a glance.
OpenAI documents a 131,072-token context window. Input modalities: text. Output: text. Pricing status: Self-hosted.
MODEL IDgpt-oss-120b
CONTEXT WINDOW131,072tokens
MAX OUTPUT131,072
KNOWLEDGE CUTOFF2024-06-01
STANDARD RATENot publishedper 1 million tokens
OUTPUT RATE—per 1 million tokens
CAPABILITY CONTRACT
Published model behavior.
text
Input modalities come from the cited official model documentation.
text
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
Self-hosted.
Self-hosted.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
What the source record does not assume.
01
OpenAI explicitly states that gpt-oss models are not served through the OpenAI API and have no OpenAI API pricing.
02
The model is distributed under Apache 2.0 and can run on self-managed infrastructure or third-party hosting providers.
EXPLORE
Keep the model in context.
OFFICIAL SOURCES
Verification links.
WHAT CHANGED
gpt-oss-120b: what changed.
No post-baseline factual changes recorded for gpt-oss-120b since 2026-10-07.
VERIFIED BASELINE2026-10-07Current facts remain aligned with the SXF ledger.
VERIFIED CHANGE HISTORY
gpt-oss-120b verified history.
gpt-oss-120b
Baseline verified: 131,072 context · 131,072 max output
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head 8e73a9cb15ea…