Open-source 120B parameter model with reasoning capabilities via Groq inference.
PassingRight routes requests to the best providers that are able to handle your prompt size and parameters.
Open-source 120B parameter model with reasoning capabilities via Groq inference. You can access it through PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for GPT OSS 120B on PassingRight starts at $0.03 per million input tokens and $0.14 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
GPT OSS 120B supports a context window of up to 131,072 tokens on its largest provider deployment.
GPT OSS 120B is served by ByteDance, Groq, Cerebras, Runware, Together AI, Azure, SCX.ai (Turbo) through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
GPT OSS 120B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
GPT OSS 120B was released on August 5, 2025.
GPT-6 Sol
Up to 10% off1,050,000 context$1.80 in / $9.00 out per 1M
GPT-6 Luna
Up to 10% off1,050,000 context$0.09 in / $0.45 out per 1M
GPT Image 2.5 Flare
Up to 10% off$4.50 in / $0.00 out per 1M
GPT Image 2.5 Sunburst
Up to 10% off$4.50 in / $0.00 out per 1M
GPT-6 Astra
Up to 10% off1,050,000 context$9.00 in / $45.00 out per 1M
GPT Transcribe
Up to 10% off$0.00 in / $0.00 out per 1M