tokenstat
tokenstat
Abacus

Gemini 3.1 Pro Preview

abacus/gemini-3.1-pro-preview · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$2
$/MTok · models.dev
Cheapest output
$12
$/MTok
Context
1.0M
tokens
Offers
11
2 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
models.devcheapestgemini-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-previewGitHub Copilot$2$12$0.21M
models.devgemini-3.1-pro-previewGoogle Vertex AI$2$12$0.21.0M
models.devgemini-3.1-pro-previewLLM Gateway$2$12$0.21.0M
models.devgemini-3.1-pro-previewVivgrid$2$12$0.21.0M
LiteLLMgemini-3.1-pro-preview$2$12$0.2
models.devgemini-3-1-pro-previewVenice AI$2.50$15$0.51M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: audio
  • In: video
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-01Released: 2026-02-19Family: gemini-pro

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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