AiCostCompare

Gemini 3.6 Flash vs GPT-6.1 Terra (batch)

Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and GPT-6.1 Terra (batch) (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 14, 2026, 8:52 AM UTC · refreshed nightly

Gemini 3.6 Flash

Google

GPT-6.1 Terra (batch)

OpenAI

Pricing
Input $/1M$0.75$0.50
Output $/1M$3.75$2.50
Blended $/1M (3:1)$1.50$1.00
RAG example (30K in / 2K out)$0.03$0.02
Quality & speed
Intelligence Index—51.3
Coding Index69.2—
Agentic Index29—
Output speed (tok/s)——
Time to first token——
Specs
Context window1.05M1.05M
Input modalitiestext, image, video, file, audiofile, image, text

FAQ

Which is cheaper, Gemini 3.6 Flash or GPT-6.1 Terra (batch)?

GPT-6.1 Terra (batch) has the lower blended API price at $1.00 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-6.1 Terra (batch) costs about $0.02 per request versus $0.03. Also compare context windows: Gemini 3.6 Flash offers 1.05M and GPT-6.1 Terra (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

GPT-6.1 Terra (batch) leads on the Artificial Analysis Intelligence Index (51.3 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.