Gemini 3 Flash API Pricing
Gemini 3 Flash is a fast, multimodal language model for real-time text generation. Supports text and image inputs, function calling, and Google Search grounding. Token-based pricing: $0.30/M input tokens and $1.80/M output tokens. Two endpoints: standard async (/gemini-3-flash) and live streaming (/gemini-3-flash/stream) via SSE.
About Gemini 3 Flash
Gemini 3 Flash is a high-speed, multimodal language model built for real-time text generation. It handles text and image inputs natively, supports function calling and Google Search grounding, and delivers low-latency responses — making it ideal for chatbots, assistants, content tools, and automation pipelines. Pricing is token-based: $0.30 per million input tokens and $1.80 per million output tokens.
Interactive Savings Calculator
Estimate monthly API spend and compare absolute developer savings.
$3000.00
$0.30/M input tokens, $1.80/M output tokens$5000.00
$0.50/M input tokens, $3.00/M output tokensDetailed Pricing Breakdown
| Provider | Estimated Rate | Notes |
|---|---|---|
| Google AI (Official) | $0.50/M input tokens, $3.00/M output tokens | Official Google AI pricing for Gemini Flash. muapiapp is 40% cheaper — you save $0.20 per million input tokens and $1.20 per million output tokens. |
| muapiapp | $0.30/M input tokens, $1.80/M output tokens | 40% cheaper than Google's official pricing. Token-based billing — you only pay for what you use, with no per-request minimums or setup fees. |
| Fal.ai | Not available | Fal.ai does not currently offer Gemini Flash as a standalone LLM endpoint. |
| Replicate | Not available | Replicate does not currently offer Gemini Flash as a hosted model. |
Developer Integration Snippets
Model FAQ
Compare similar models
Ready to scale your production?
Get instant access to developer keys. Integrate high-speed dynamic models in minutes with our robust SDKs.