AiCostCompare

Gemini 3.6 Flash vs gpt-oss-120b

Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and gpt-oss-120b (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 11:46 AM UTC · refreshed nightly

Gemini 3.6 Flash

Google

gpt-oss-120b

OpenAI

Pricing
Input $/1M$0.75$0.15
Output $/1M$3.75$0.60
Blended $/1M (3:1)$1.50$0.262
RAG example (30K in / 2K out)$0.03$0.0057
Quality & speed
Intelligence Index—3.8
Coding Index69.230.4
Agentic Index293.7
Output speed (tok/s)——
Time to first token——
Specs
Context window1.05M131K
Input modalitiestext, image, video, file, audiotext

FAQ

Which is cheaper, Gemini 3.6 Flash or gpt-oss-120b?

gpt-oss-120b has the lower blended API price at $0.262 per 1M tokens (3:1 input:output mix), versus $1.50 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), gpt-oss-120b costs about $0.0057 per request versus $0.03. Also compare context windows: Gemini 3.6 Flash offers 1.05M and gpt-oss-120b offers 131K.

Which scores higher on Artificial Analysis benchmarks?

gpt-oss-120b leads on the Artificial Analysis Intelligence Index (3.8 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.