Which is cheaper, Gpt Oss 120b or Gpt 3 5 Turbo Instruct?
Gpt Oss 120b costs $0.35/M input; Gpt 3 5 Turbo Instruct costs $1.5/M input. Price spread matters at billion-token scale.
Gateway catalog snapshot.
Gpt Oss 120b is cheaper at $0.35/M input vs $1.5/M input for Gpt 3 5 Turbo Instruct. Compare context, hosts, and o10 routing bands.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
Gpt Oss 120b vs Gpt 3 5 Turbo Instruct. Price, context, routing
On this page
AnswersSelf-contained
How do Gpt Oss 120b and Gpt 3 5 Turbo Instruct context windows compare?
Gpt Oss 120b: 131,072 tokens. Gpt 3 5 Turbo Instruct: 8,192 tokens.
01Deep dive
Comparison summary
Gpt Oss 120b is cheaper at $0.35/M input vs $1.5/M input for Gpt 3 5 Turbo Instruct. Compare context, hosts, and o10 routing bands.
Gpt Oss 120b is cheaper at $0.35/M input vs $1.5/M input for Gpt 3 5 Turbo Instruct. Compare context, hosts, and o10 routing bands.
SourceMethodology
o10 gateway + fulfillment catalog snapshot.
FAQFrequently asked questions
Common questions
Which is cheaper, Gpt Oss 120b or Gpt 3 5 Turbo Instruct?
Gpt Oss 120b at $0.35/M input vs $1.5/M for Gpt 3 5 Turbo Instruct.
Can you run both on the same hosts?
Gpt Oss 120b: OpenRouter, NVIDIA NIM. Gpt 3 5 Turbo Instruct: OpenRouter.