gpt-oss-120b
Model ID: openai/gpt-oss-120b · Context window: 131K tokens
All rates, conditions and sources
Conditions of every rate below:
- SiliconFlow international pricing page (www.siliconflow.com/pricing), LLM table: input, cached-input and output prices per 1 million tokens ("Prices shown are per 1 million tokens.").
- Model "openai/gpt-oss-120b" (the SiliconFlow API model ID), the row "gpt-oss-120b" whose Details link is the model page ./models/gpt-oss-120b; that page was reviewed on 2026-10-16 to name this ID, which was in SiliconFlow's authenticated model list.
- Currency: the page writes a bare "$" and names no currency; compute.info's owner confirmed on 2026-10-16 that these are US dollars.
- Cache: SiliconFlow's pricing page, model pages and prompt-caching article (reviewed 2026-10-16 and 2026-10-17) state no cache duration, cache-write price or exact eligibility rule. A missing cache-read price is unknown, not zero.
- This row also lists a cached-input price above its input price; it is not published as a cache-read rate while the page is inconsistent.
- List prices: the page states no region, endpoint, tier or account eligibility, and its FAQ offers volume discounts by arrangement.
Input: $0.05 per 1M tokens · Standard tier
- Input tokens (the row's "Input (/M Tokens)" column).
Output: $0.45 per 1M tokens · Standard tier
- Output tokens (the row's "Output (/M Tokens)" column).
Capability (Epoch AI): ECI 140.2 (90% range 138.3–142.1) · range spans bands · Epoch AI score for gpt-oss-120b, model dated Aug 5, 2025
Price observed:
API availability: listed as available when checked (not a live service check)
Collection record
Primary source ↗ · provider documentation · Claims: siliconflow-gpt-oss-120b: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A
- Official SiliconFlow model page for openai/gpt-oss-120b, spec block, raw SHA-256 0bbdc3fcb53a582e67c93295ceabaa114604dcc1cfc492f4a76b1313c9f1b843 (the #104 identity review's copy, docs/provenance/siliconflow-identity-2026-10-16.json; the retrieval time is that copy's file time, an upper bound on the read): "Context length 131K".
- Visible shorthand recorded as stated (#504); not converted to an exact token count. The pricing page's LLM table states the same value in its Context Length column; the SiliconFlow parser fails closed if it ever differs (#626).
- Specifications only: no pricing, availability, capability or release-date assertion.
Primary source ↗ · provider documentation · Claims: siliconflow-gpt-oss-120b: pricing · siliconflow-gpt-oss-120b: availability · 52 more claims about 26 other catalog entries · Retrieved · Checked · Review due · Confidence: B
- Raw SHA-256: 74219c83c4ffeeed010e2f82509ddd413f75f6376836e282985a75dea97c51ef; collector siliconflow-pricing-llm-table-1.
- Hosted listing and pricing observation only: the reviewed LLM rows of the international pricing page; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers, a listing is not proof of identical weights or behavior.
- The page shows prices with a bare "$"; US dollars rests on the owner's confirmation of 2026-10-16 (#104), not on the page, hence confidence B. Its server-rendered LLM table is not a complete inventory (Load More), so an unlisted model is not evidence of anything.