AiCostCompare

Gemini 3.6 Flash vs GPT-3.5 Turbo (older v0613)

Side-by-side API pricing and Artificial Analysis performance for Gemini 3.6 Flash (Google) and GPT-3.5 Turbo (older v0613) (OpenAI). Green cells mark the better value in each row.

Prices updated Jul 22, 2026, 1:33 AM UTC · refreshed hourly

Gemini 3.6 Flash

Google

GPT-3.5 Turbo (older v0613)

OpenAI

Pricing
Input $/1M$1.50$1.00
Output $/1M$7.50$2.00
Blended $/1M (3:1)$3.00$1.25
RAG example (30K in / 2K out)$0.06$0.034
Quality & speed
Intelligence Index50.1
Coding Index69.2
Agentic Index38.7
Output speed (tok/s)3010
Time to first token11.80s0s
Specs
Context window1.05M4K
Input modalitiestext, image, video, file, audiotext

FAQ

Which is cheaper, Gemini 3.6 Flash or GPT-3.5 Turbo (older v0613)?

GPT-3.5 Turbo (older v0613) has the lower blended API price at $1.25 per 1M tokens (3:1 input:output mix), versus $3.00 for the other model. Prices are live from OpenRouter and refresh about hourly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), GPT-3.5 Turbo (older v0613) costs about $0.034 per request versus $0.06. Also compare context windows: Gemini 3.6 Flash offers 1.05M and GPT-3.5 Turbo (older v0613) offers 4K.

Which scores higher on Artificial Analysis benchmarks?

Gemini 3.6 Flash leads on the Artificial Analysis Intelligence Index (50.1 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.