GPT OSS 120B vs Qwen3.5 Flash

01Differences

At a glance

Computed automatically from tracked data.

• GPT OSS 120B's input price is 3% lower than Qwen3.5 Flash's ($0.03 vs $0.03 per 1M).
• GPT OSS 120B's output price is 187% higher than Qwen3.5 Flash's ($0.10 vs $0.29 per 1M).
• Qwen3.5 Flash has a 7.8× larger context window (1,020,000 vs 131,072 tokens).
• They differ in open weights (GPT OSS 120B: Yes, Qwen3.5 Flash: No).
02Specs

Side by side

GPT OSS 120BQwen3.5 Flash
Input / 1M$0.03$0.03
Output / 1M$0.10$0.29
Context131,0721,020,000
Max output131,0721,020,000
Providers608
Released2025-08-052026-02-23
03Prices

Common providers

ProviderGPT OSS 120BQwen3.5 Flash
merge-gateway$0.09 / $0.36$0.03 / $0.29
nano-gpt$0.35 / $0.75$0.10 / $0.40
orcarouter$0.03 / $0.17$0.10 / $0.40
vercel$0.10 / $0.50$0.10 / $0.40
04History

Recent changes

GPT OSS 120B
2026-09-15Price cut edenai
2026-09-15Price cut edenai
2026-09-15Price cut edenai
2026-09-15Price cut edenai
2026-09-14Price cut edenai
Qwen3.5 Flash
2026-09-10Added ofox
2026-08-27Added orcarouter
2026-08-09Added merge-gateway
2026-08-07Added empiriolabs
2026-08-07Context nano-gpt
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews