tokenstat
tokenstat

Google: Gemini 3 Pro Preview

gemini/gemini-3-pro-preview · rates as of · Benchmarks · AI plans · Calculator

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Cheapest input
$0.57
$/MTok · models.dev
Cheapest output
$3.43
$/MTok
Context
1.0M
tokens
Sources
2
10 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestgemini-3-pro-previewQiHang$0.57$3.43$01M
models.devgemini-3-pro-previewJiekou.AI$1.80$10.80$01.0M
models.devgoogle/gemini-3-pro-previewMerge Gateway$2$12$0.21.0M
models.devgemini-3-pro-preview302.AI$2$12$01M
models.devgemini-3-pro-previewHelicone$2$12$0.21.0M
LiteLLMgoogle/gemini-3-pro-previewN/A$2$12$0.2N/A
LiteLLMgemini-3-pro-previewN/A$2$12$0.2N/A
LiteLLMgemini/gemini-3-pro-previewN/A$2$12$0.2N/A
LiteLLMopenrouter/google/gemini-3-pro-previewN/A$2$12$0.2N/A
LiteLLMvertex_ai/gemini-3-pro-previewN/A$2$12$0.2N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • In: audio
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-11-19Family: gemini-pro

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.