Google

Gemma 4 31B (Non-reasoning)

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

Pricing (per 1M tokens)

Input$0.15
Output$0.40
Blended (3:1)$0.21

Source: Artificial Analysis

Performance

Output Speed82 tok/s
Time to First Token1400ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Gemma 4 31B (Non-reasoning) is a budget-tier option from Google at $0.40/M output tokens. Despite the low price, it scores competitively on Coding Index (33.2) and Intelligence Index (22.3) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Gemma 4 31B (Non-reasoning) reports 82 tok/s output speed and 1400ms 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 31B (Non-reasoning) costs $0.19 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 31B (Non-reasoning)Current
$0.15$0.4082 tok/s
GPT-5 nano (minimal)
$0.05$0.40161 tok/s
Hermes 4 - Llama-3.1 70B (Non-reasoning)
$0.13$0.4056 tok/s
Llama Nemotron Super 49B v1.5 (Non-reasoning)
$0.40$0.4090 tok/s
GLM-4.7-Flash (Reasoning)
$0.07$0.4093 tok/s
Jamba 1.5 Mini
$0.20$0.40

Example Costs

Single Request
$0.0003
1.0K in / 500 out
1K Requests/day
$0.3500
1.0M in / 500.0K out
10K Requests/day
$3.50
10.0M in / 5.0M out