Best Claude model for agents and automations
For agents and automations with Claude, use Sonnet 5.5 at medium effort.
Sonnet 5.5 at medium effort
Medium efforteffort = medium
Ties Opus on the Vals Index (67.0%, measured at max effort) at about two-thirds of the cost per task. For long, messy runs of several hours, step up to high.
How it compares
Prices are in US dollars per million tokens, input then output. Sonnet 5.5 costs $2 / $10.
| Model | Price | Against the pick |
|---|---|---|
| Opus 5.5 | $4 / $20 | Same Vals score, about 1.5x the cost per task. |
| Fable 5.1 | $10 / $50 | Built for very long autonomous work, at five times Sonnet's price. |
| Haiku 5.5 | $0.10 / $0.50 | Good as a cheap worker inside a bigger pipeline. |
Setting it in the API
In an API request, set the model and effort like this:
model: "claude-sonnet-5-5", output_config: { effort: "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
Claude for code, everyday work, research.
Other labs for agents and automations: OpenAI, Gemini.
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.
