GPT OSS 120B High: API Pricing, Context Window & Benchmarks
GPT OSS 120B High is a language model from OpenAI, released in August 2025.
GPT-OSS-120B High provides enhanced reasoning capabilities with high-effort thinking for complex problems. This variant offers deeper analysis and more thorough responses compared to the base model, making it ideal for challenging tasks
GPT OSS 120B High benchmarks
Rankings
Quality Tracker
GPT OSS 120B High Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Jul 21 2026GPT OSS 120B High pricing
Providers
GPT OSS 120B High starts at $0.100 per million input tokens and $0.500 per million output tokens via OpenAI. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $0.100 | $0.500 | 131.1K/131.1K | —/6.50 | 100/— | — | / |
 Fireworks | $0.150 | $0.600 | 131.0K/30.0K | 0.00/0.00 | —/— | 0.00%(78) | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
GPT OSS 120B High model size
GPT OSS 120B High has 116.8 billion parameters. See how it compares to other models in the same parameter range.
GPT OSS 120B High context window
Input and output token limits for GPT OSS 120B High, plus how it ranks on long-context understanding.
GPT OSS 120B High latency
GPT OSS 120B High time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
GPT OSS 120B High examples
Recent arena outputs from GPT OSS 120B High, picked from the highest-ranked matchups.
GPT OSS 120B High license
GPT OSS 120B High is released under the Apache 2.0 license, which permits commercial use, has 116.8B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 116.8B
Apache License 2.0 - allows commercial use
GPT OSS 120B High resources
Official sources for GPT OSS 120B High: official playground, paper or system card, official launch post, source repository, model weights.
GPT OSS 120B High vs other models
The most-compared alternatives to GPT OSS 120B High are Seed 2.0 Lite, K-EXAONE-236B-A23B, LongCat-Flash-Thinking-2601. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT OSS 120B High
Models ranked just above and below GPT OSS 120B High by LLM Stats score.
FAQ
Common questions about GPT OSS 120B High.