tokenstat
tokenstat
Abacus

Gemini 3.5 Flash

abacus/gemini-3.5-flash · rates as of · Benchmarks · Plans · Calculator

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Cheapest input
$0.1857
$/MTok · models.dev
Cheapest output
$1.11
$/MTok
Context
1.0M
tokens
Offers
13
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-3.5-flashUnoRouter$0.1857$1.11$01.0M
models.devgemini-3.5-flashAbacus$1.50$9$0.151.0M
models.devgemini-3.5-flashAIHubMix$1.50$9$1.501M
models.devgemini-3.5-flashGitHub Copilot$1.50$9$0.15200K
models.devgemini-3.5-flashGoogle Vertex AI$1.50$9$0.151.0M
models.devgemini-3.5-flashLLM Gateway$1.50$9$0.151.0M
models.devgemini-3-5-flashNeon$1.50$9$0.151.0M
models.devgemini-3.5-flashOpenCode Zen$1.50$9$0.151.0M
models.devgemini-3.5-flashPioneer$1.50$9$0.151.0M
models.devgemini-3.5-flashSAP AI Core$1.50$9$0.151.0M
LiteLLMgemini-3.5-flash$1.50$9$0.15
models.devgemini-3-5-flashVenice AI$1.55$9.45$0.1551M
models.devgemini-3.5-flashXpersona$1.55$12.20$0.1551M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: audio
  • In: video
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-01Released: 2026-05-19Family: gemini-flash

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