New: Nano Banana 2.1Try the model
API Stock
All models

Google

Gemini API

Google's Gemini Flash tiers, from the efficient 3.5 to the newest 3.8.

At a glance

From
$0.9 / 1M tokens

Models in this family

ModelFromModesOpen
Gemini 3.8 FlashLatest Gemini Flash tier — fast multimodal reasoning at a low token price.$0.9/ 1M tokens—OpenDocs
Gemini 3.7 FlashLatest Gemini Flash tier — fast multimodal reasoning at a low token price.$0.9/ 1M tokens—OpenDocs
Gemini 3.6 FlashHigh-efficiency Google model for coding, agentic workflows and web/app development. 1M-token context, text/image/audio/video/file input.$0.9/ 1M tokens—OpenDocs
Gemini 3.5 FlashFast general-purpose chat and structured generation through the OpenAI protocol.$0.9/ 1M tokens—OpenDocs

Pricing

ModelOptionPrice
Gemini 3.8 Flashinput$0.9/ 1M tokens
Gemini 3.8 Flashoutput$4.5/ 1M tokens
Gemini 3.8 FlashcacheRead$0.09/ 1M tokens
Gemini 3.7 Flashinput$0.9/ 1M tokens
Gemini 3.7 Flashoutput$4.5/ 1M tokens
Gemini 3.7 FlashcacheRead$0.09/ 1M tokens
Gemini 3.6 Flashinput$0.9/ 1M tokens
Gemini 3.6 Flashoutput$4.5/ 1M tokens
Gemini 3.6 FlashcacheRead$0.09/ 1M tokens
Gemini 3.5 Flashinput$0.9/ 1M tokens
Gemini 3.5 Flashoutput$5.4/ 1M tokens
Gemini 3.5 FlashcacheRead$0.09/ 1M tokens

Which one to pick

  • Gemini 3.8 Flash

    The newest Flash tier — fast multimodal reasoning at the same low token price as 3.7.

  • Gemini 3.7 Flash

    Previous Flash tier for existing integrations.

  • Gemini 3.6 Flash

    Aimed at coding and agentic work, with a 1M-token context and image, audio, video and file input — priced the same as 3.7.

  • Gemini 3.5 Flash

    General-purpose chat and structured generation at the standard reasoning budget.

Strengths

  • 3.6 Flash accepts image, audio, video and file input, which is the broadest input surface in our text lineup.
  • A 1M-token context on 3.6 Flash without moving to a frontier-priced model.
  • The two newest tiers cost the same, so moving from 3.7 to 3.8 is a model-name change with no price step.

Limitations

  • Cache reads are supported but cache writes are not priced here, so caching behaviour differs from the GPT and Claude lines.
  • These are Flash tiers only — Google's largest Gemini models are not in this family.

Frequently asked questions

How much does the Gemini API cost?

API Stock bills per use from one prepaid balance, with no subscription. Current prices: Gemini 3.8 Flash — $0.9 per 1M input tokens and $4.5 per 1M output tokens; Gemini 3.7 Flash — $0.9 per 1M input tokens and $4.5 per 1M output tokens; Gemini 3.6 Flash — $0.9 per 1M input tokens and $4.5 per 1M output tokens; Gemini 3.5 Flash — $0.9 per 1M input tokens and $5.4 per 1M output tokens.

Which Gemini model is the cheapest?

Gemini 3.8 Flash is the cheapest at $0.9 per 1M input tokens. The most expensive tier, Gemini 3.5 Flash, costs $0.9 per 1M input tokens.

Does the Gemini API support prompt caching?

Yes. Cached input tokens are billed at a lower rate: Gemini 3.8 Flash — $0.09 instead of $0.9 per 1M tokens; Gemini 3.7 Flash — $0.09 instead of $0.9 per 1M tokens; Gemini 3.6 Flash — $0.09 instead of $0.9 per 1M tokens; Gemini 3.5 Flash — $0.09 instead of $0.9 per 1M tokens.

Can I use the Gemini API with the OpenAI or Anthropic SDK?

Yes. Gemini models accept the OpenAI request format: set the SDK's base URL to https://api.api-stock.com/api/v1 and use your API Stock API key. Switching between models only changes the model id.

How do I get an API key for Gemini?

Create an account and API key on API Stock, then fund your balance. The same key works with Gemini and other catalog models.

The vendor's own description of this line: Google DeepMind — Gemini

Guides