Google AI · gemini-3-flash

Gemini 3 Flash pricing (October 2026)

Google AI lists Gemini 3 Flash at $0.50 per 1M input tokens and $3.00 per 1M output tokens.

On Crazyrouter the same model is $0.165 / $1.32 — 67% below list price.

That is $0.0005 / $0.003 per 1K tokens. Gemini 3 Flash is the #9 cheapest of the 38 chat models we track, by input price. 1.5× cheaper than Gemini 3.8 Flash. Through Crazyrouter you save $0.335 on every 1M input tokens versus list.

Call Gemini 3 Flash at $0.165 in / $1.32 out per 1M tokens. Same model, same API, no plan — pay per token.

Looking for the ChatGPT / Claude app subscription price? That is a separate consumer product sold by Google AI. This page is the developer API price per token.

Gemini 3 Flash price by provider

USD per 1M tokens. Cloud prices are the base tier in the default region; the linked source is authoritative.

ProviderInputCached inputOutputContextSource
Google AI$0.50$0.05$3.001.0MGoogle AI
AzureNo verified quote
AWS BedrockNo verified quote
Google Vertex AI$0.50$0.05$3.001.0MGoogle Vertex AI
OpenRouterNo verified quote
Crazyrouter$0.165$0.0165$1.321.0Mcrazyrouter.com

per 1M tokens · Snapshot Oct 24, 2026

What Gemini 3 Flash costs per month

Three typical workloads, priced on each provider from the table above.

WorkloadGoogle AIGoogle Vertex AICrazyrouter
Prototype: 10M in / 2M out$11.00$11.00$4.29
Product: 100M in / 20M out$110.00$110.00$42.90
Scale: 1B in / 200M out$1,100$1,100$429.00

Price changes

  • Jan 6, 2026 — OpenRouter started listing Gemini 3 Flash at $0.50 / $3.00 per 1M.
  • Dec 17, 2025 — Google Vertex AI started listing Gemini 3 Flash at $0.50 / $3.00 per 1M.
  • Dec 17, 2025 — Google AI started listing Gemini 3 Flash at $0.50 / $3.00 per 1M.

Alternatives to Gemini 3 Flash

Same-family models and cheaper options for similar tasks.

Gemini 3 Flash pricing FAQ

How much does Gemini 3 Flash cost?

Google AI charges $0.50 per 1M input tokens and $3.00 per 1M output tokens. Through Crazyrouter the same model is $0.165 / $1.32.

What is cached input pricing?

Tokens that repeat an earlier prompt prefix are billed at the cached rate ($0.05 per 1M when supported) instead of the full input price.

Is there a batch discount?

Yes. Google AI offers batch pricing at $0.25 in / $1.50 out per 1M tokens for asynchronous jobs.

Is Gemini 3 Flash cheaper on Azure, Bedrock or Vertex?

Cloud providers usually match the list price and add regional or provisioned tiers; see the table above for the base rate on each. Crazyrouter applies its discount on top of list.

Sources and method

Provider reference prices use LiteLLM data and maintained entries. Provider links are references, not proof of daily official verification. Snapshot: Oct 24, 2026. Crazyrouter rates come from our billing table; confirm current prices, region and terms with the provider before purchase.

Further reading