Google

Gemma 4 E4B (Non-reasoning)

AI model by Google. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.02
Output$0.10
Blended (3:1)$0.04

Source: Artificial Analysis

Performance

Output Speed56 tok/s
Time to First Token700ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. Gemma 4 E4B (Non-reasoning) is a budget-tier option from Google at $0.10/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Gemma 4 E4B (Non-reasoning) reports 56 tok/s output speed and 700ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, Gemma 4 E4B (Non-reasoning) costs $0.03 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Gemma 4 E4B (Non-reasoning)Current
$0.02$0.1056 tok/s
Ministral 3 3B
$0.10$0.10205 tok/s
Granite 4.1 8B
$0.05$0.10117 tok/s
Sarvam 30B (high)
$0.03$0.11
Nova Micro
$0.04$0.14282 tok/s
Llama 3 Instruct 8B
$0.04$0.14

Example Costs

Single Request
<$0.0001
1.0K in / 500 out
1K Requests/day
$0.0700
1.0M in / 500.0K out
10K Requests/day
$0.7000
10.0M in / 5.0M out