tokenstat
tokenstat
Google

Google: Gemini 3.1 Pro Preview

gemini/gemini-3.1-pro-preview · rates as of · How this catalog is built · Benchmarks

Reasoning-first Gemini preview for agentic coding and complex problem solving

Cheapest input
$1
$/MTok · models.dev
Cheapest output
$6
$/MTok
Context
1.0M
tokens
Sources
3
36 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $12 → $6
  • ↓ lowerInput $2 → $1

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.devcheapestgoogle/gemini-3.1-pro-previewKilo Gateway$1$6$0.11.0M
OpenRoutergoogle/gemini-3.1-pro-preview:batchOpenRouter$1$6$01.0M
models.devgoogle/gemini-3.1-pro-previewAI/ML API$2$12$0.51M
models.devgoogle/gemini-3.1-pro-previewEden AI$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewFastRouter$2$12$0.21.0M
models.devgemini-3.1-pro-previewGoogle$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewImpossibl$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewMerge Gateway$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewNanoGPT$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewOfox$2$12$0.21.0M
OpenRoutergoogle/gemini-3.1-pro-previewOpenRouter$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewOrcaRouter$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewPerplexity$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewPrime Inference$2$12$01.0M
models.devgoogle/gemini-3.1-pro-previewStandard Compute$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewTempr Gateway$2$12$0.21.0M
models.devgoogle/gemini-3.1-pro-previewVercel AI Gateway$2$12$0.21M
models.devgoogle/gemini-3.1-pro-previewZenMux$2$12$0.21.0M
models.devgemini-3.1-pro-preview302.AI$2$12$01.0M
models.devgemini-3.1-pro-previewAbacus$2$12$0.21.0M
models.devgemini-3.1-pro-previewAIHubMix$2$12$0.21.0M
models.devgemini-3.1-pro-previewAuriko$2$12$0.21.0M
models.devgemini-3.1-pro-previewDaoXE$2$12$0.21.0M
models.devgemini-3-1-pro-previewFrogBot$2$12$0.21M
models.devgemini-3.1-pro-previewGoogle Vertex AI$2$12$0.21.0M
models.devgoogle-ai-studio/gemini-3.1-pro-previewLLM Gateway$2$12$0.21.0M
models.devgemini-3.1-pro-previewDevPass (LLM Gateway)$2$12$0.21.0M
models.devgemini-3.1-pro-previewOpper$2$12$0.21.0M
models.devgemini-3.1-pro-previewRequesty$2$12$0.21.0M
models.devgemini/gemini-3.1-pro-previewCrossModel$2$12$0.21.0M
LiteLLMgemini-3.1-pro-previewN/A$2$12$0.2N/A
LiteLLMgemini/gemini-3.1-pro-previewN/A$2$12$0.2N/A
LiteLLMperplexity/google/gemini-3.1-pro-previewN/A$2$12$0.2N/A
LiteLLMvertex_ai/gemini-3.1-pro-previewN/A$2$12$0.2N/A
models.devgemini-3-1-pro-previewVenice AI$2.50$15$0.51M
models.devgemini-3.1-pro-previewVivgrid$3$12$0.31.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • In: audio
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-01Released: 2026-02-19Output limit: 66K tokensFamily: gemini-pro

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload