Best Gemini model for research
For research with Gemini, use 3.8 Flash at high effort.
3.8 Flash at high effort
High effortgeneration_config.thinking_level = high
Beats 3.1 Pro on 9 of 13 shared benchmarks at about a third of the price.
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 | Tops the Vals Index (68.9%), but most accounts can't use it yet. |
| 3.1 ProPreview | $2 / $12 | Edges Flash on a few knowledge tests and loses most others, at about 3x the price. |
| 3.5 Flash-Lite | $0.30 / $2.50 | Too light for deep work. |
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: "high" }
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, agents and automations.
Other labs for research: 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.
