Log in
← All models

Gemini 3.5 Flash

Balanced

Fast, capable, and cheap — a favourite default for high-throughput agents.

Google
Maker
89/100
Overall
52
Value score
$3.75
Blended /1M
1.0M
Context
Proprietary
Weights
Pricing: $1.50 in · $9.00 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality8.9/10 · 77% community
Agentic Ability8.9/10 · 77% community
Speed9.4/10 · 79% community
Value for $8.7/10 · 76% community
Reliability8.9/10 · 77% community

Gemini 3.5 Flash pairs strong quality with high speed and a 1M-token context, making it a popular default for agents that make many calls. It's the value pick in Google's lineup before stepping up to Pro.

Strengths
  • Fast with a 1M context
  • Multimodal
  • Great price for the quality
Trade-offs
  • Below Pro on hard reasoning
  • Occasional verbosity

Agents that run Gemini 3.5 Flash well

High-throughput agents that need big context cheaply.

Best model for Gemini CLIBest model for ClineBest model for ContinueBest model for OpenClawBest model for HermesBest model for OpenCode

Gemini 3.5 Flash FAQ

Is Gemini 3.5 Flash good for AI agents?
High-throughput agents that need big context cheaply. On our editorial scoring it rates 8.9/10 for agentic ability and 8.9/10 for output quality. Fast with a 1M context.
How much does Gemini 3.5 Flash cost?
Via OpenRouter, Gemini 3.5 Flash is priced at $1.50 in · $9.00 out / 1M tokens — a blended rate of about $3.75 per 1M tokens for typical input-heavy agent use.
What is Gemini 3.5 Flash's context window?
Gemini 3.5 Flash has a 1.0M-token context window — large enough to hold sizeable codebases or document sets in a single run. Google is the maker.
Can I self-host Gemini 3.5 Flash?
No — Gemini 3.5 Flash is a proprietary, hosted-only model from Google. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of Gemini 3.5 Flash?
The main trade-offs: below pro on hard reasoning; occasional verbosity. It's strongest for high-throughput agents that need big context cheaply.

Gemini 3.5 Flash compared

Gemini 3.5 Flash vs Sonnet 4.6Gemini 3.5 Flash vs GPT-5.4Gemini 3.5 Flash vs GPT-5.3-CodexGemini 3.5 Flash vs Kimi K2.7 CodeGemini 3.5 Flash vs MiniMax M3Gemini 3.5 Flash vs Qwen3.7 PlusGemini 3.5 Flash vs Devstral 2Gemini 3.5 Flash vs GLM 4.7

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →