tokenstat
tokenstat

Google Gemini Pro Latest

gemini/gemini-pro-latest · rates as of · Benchmarks · Plans · Calculator

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Cheapest input
$1.25
$/MTok · LiteLLM
Cheapest output
$10
$/MTok
Context
1.0M
tokens
Offers
6
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestgemini/gemini-pro-latest$1.25$10$0.125
LiteLLMcheapestgemini-pro-latest$1.25$10$0.125
models.devgemini-pro-latestLLM Gateway$2$12$0.21.0M
models.dev~google/gemini-pro-latestKilo Gateway$2$12$0.21.0M
models.devgoogle/gemini-pro-latestNanoGPT$2$12$0.21.0M
OpenRouter~google/gemini-pro-latestOpenRouter$2$12$0.21.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: audio
  • In: pdf
  • In: video
  • In: file
  • Out: text
Knowledge cutoff: 2025-01Released: 2026-04-27Family: gemini

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash