Auto-generated comparison

Anthropic: Claude 3 Haiku vs Google: Gemma 4 31B (batch)

Google: Gemma 4 31B (batch) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

CapabilityAnthropic: Claude 3 HaikuGoogle: Gemma 4 31B (batch)Winner
Context window
Maximum number of input tokens the model can attend to in a single request.
200K262K🏆 Google: Gemma 4 31B (batch)
Input price (per 1M)
Cost per million input tokens billed by the provider.
$0.25$0.39🏆 Anthropic: Claude 3 Haiku
Output price (per 1M)
Cost per million output tokens billed by the provider.
$1.25$0.97🏆 Google: Gemma 4 31B (batch)
Tool / function calling
First-class support for emitting structured tool calls.
YesYesTie
Vision input
Accepts image inputs alongside text.
YesYesTie
Reasoning mode
Internal chain-of-thought / extended-thinking support.
Yes🏆 Google: Gemma 4 31B (batch)

Frequently asked questions

Is Anthropic: Claude 3 Haiku better than Google: Gemma 4 31B (batch)?

Google: Gemma 4 31B (batch) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.

What's the price difference between Anthropic: Claude 3 Haiku and Google: Gemma 4 31B (batch)?

Input: $0.25 vs $0.39 per 1M tokens. Output: $1.25 vs $0.97 per 1M tokens.

What context windows do Anthropic: Claude 3 Haiku and Google: Gemma 4 31B (batch) support?

Anthropic: Claude 3 Haiku supports up to 200K tokens. Google: Gemma 4 31B (batch) supports up to 262K tokens.

Do both Anthropic: Claude 3 Haiku and Google: Gemma 4 31B (batch) support tool calling?

Anthropic: Claude 3 Haiku: yes. Google: Gemma 4 31B (batch): yes.

Compare Anthropic: Claude 3 Haiku with other models

Compare Google: Gemma 4 31B (batch) with other models