Gemini 3.5 Flash API pricing
View the exact Gemini model page and calculate this model's token cost.
Pricing comparison
CostRivo does not substitute a newer or merely similar model when an exact canonical participant is missing. Available participant data is still shown below with its official source.
Side-by-side model cost
Use one shared request volume and token scenario to compare selected models side by side.
Enter your usage details, then select Calculate estimate to see your projected cost.
Estimated cost = input usage cost + output usage cost + supported optional charges.
Swipe sideways to see all columns.
| Requested model | Available match | Input price | Output price | Cached input | Context window | Capabilities | Verification | Action |
|---|---|---|---|---|---|---|---|---|
Gemini Flash Exact local match | Gemini Gemini 3.5 Flash | $1.50 / 1M tokens | $9.00 / 1M tokens | Not available | 1,048,576 tokens | text, vision, audio, reasoning, function calling | Geminigemini-3.5-flashStable Official sourceVerified Sep 9, 2026. Estimates vary by usage and provider pricing conditions. | |
GPT-4o mini Missing from local data | Not available | Not available | Not available | Not available | Not available | Not available | Verification details unavailable | No route |
View the exact Gemini model page and calculate this model's token cost.
Review Gemini models, pricing sources, and provider-level cost planning.
Review OpenAI models, pricing sources, and provider-level cost planning.
Compare multiple models with one shared request and token scenario.
Compare current provider and model unit prices with verification details.
Use the pricing table for unit costs, then run the calculator with your own request and token assumptions.
Start with your highest-volume workflow because small per-request differences matter most there.
Yes. A cheaper model can cost more overall if it needs longer prompts, retries, or fallback calls.