Auto-generated comparison

google/gemma-3-4b-it vs Anthropic Claude Haiku Latest

Anthropic Claude Haiku Latest wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

Capabilitygoogle/gemma-3-4b-itAnthropic Claude Haiku LatestWinner
Context window
Maximum number of input tokens the model can attend to in a single request.
131K200K🏆 Anthropic Claude Haiku Latest
Input price (per 1M)
Cost per million input tokens billed by the provider.
$0.05$1.00🏆 google/gemma-3-4b-it
Output price (per 1M)
Cost per million output tokens billed by the provider.
$0.10$5.00🏆 google/gemma-3-4b-it
Tool / function calling
First-class support for emitting structured tool calls.
Yes🏆 Anthropic Claude Haiku Latest
Vision input
Accepts image inputs alongside text.
YesYesTie
Reasoning mode
Internal chain-of-thought / extended-thinking support.
Yes🏆 Anthropic Claude Haiku Latest

Frequently asked questions

Is google/gemma-3-4b-it better than Anthropic Claude Haiku Latest?

Anthropic Claude Haiku Latest wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.

What's the price difference between google/gemma-3-4b-it and Anthropic Claude Haiku Latest?

Input: $0.05 vs $1.00 per 1M tokens. Output: $0.10 vs $5.00 per 1M tokens.

What context windows do google/gemma-3-4b-it and Anthropic Claude Haiku Latest support?

google/gemma-3-4b-it supports up to 131K tokens. Anthropic Claude Haiku Latest supports up to 200K tokens.

Do both google/gemma-3-4b-it and Anthropic Claude Haiku Latest support tool calling?

google/gemma-3-4b-it: not advertised. Anthropic Claude Haiku Latest: yes.

Compare google/gemma-3-4b-it with other models

Compare Anthropic Claude Haiku Latest with other models