Best Gemini model for agents and automations
For agents and automations with Gemini, use 3.8 Flash at medium effort.
3.8 Flash at medium effort
Medium effortgeneration_config.thinking_level = medium
Powers Google's own managed agents. Medium is Google's recommended level for agent work.
How it compares
Prices are in US dollars per million tokens, input then output. 3.8 Flash costs $0.75 / $3.75.
| Model | Price | Against the pick |
|---|---|---|
| ArgonRolling out | $2 / $10 | Number one on AutomationBench (51.3%), but not broadly available yet. |
| 3.1 ProPreview | $2 / $12 | Older and pricier. Flash is ahead on agentic tests. |
| 3.5 Flash-Lite | $0.30 / $2.50 | Fine for simple tool calls. |
Setting it in the API
In an API request, set the model and effort like this:
model: "gemini-3.8-flash", generation_config: { thinking_level: "medium" }
Maintained by the AI team at Vegan Hacktivists
Prices are per million tokens, input / output. We pick for the best result per dollar, so a pricier model can score higher and still lose out. This pick last changed Oct 9, 2026. Sources: Anthropic docs, OpenAI docs, Gemini docs, Artificial Analysis, Vals AI.Last checked Oct 12, 2026.
Other picks
Gemini for code, everyday work, research.
Other labs for agents and automations: Claude, OpenAI.
Open the interactive picker to switch between labs and tasks.
Want helpputting this to work?
Vegan Hacktivists offers free AI and automation support to animal protection organizations — from a first conversation to a full build.
