Google

Gemma 4 31b API Pricing

Gemma 4 31b costs $0.12 per 1M input tokens and $0.35 per 1M output tokens on Google's API. Prices are provider list prices in USD, refreshed as sources update; see the Gemma 4 31b model profile for capability scores.

Input / 1M
$0.12
Output / 1M
$0.35
Effective / 1M I/O
$0.3359
Cost Rank
#8

Price List

RatePrice (USD)Notes
Input$0.12per 1M tokens
Output$0.35per 1M tokens
Blended input + output$0.471M in + 1M out at list price
Context window256K tokens

What a Workload Costs

Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of Gemma 4 31b.

WorkloadCostTokens
Short chat turn$0.000301K in / 500 out
Summarize a long document$0.013100K in / 2K out
Agentic coding session$0.095500K in / 100K out
1M input + 1M output tokens$0.4701M in / 1M out

Effective Cost

In AI IQ's scoring, Gemma 4 31b's list price is adjusted by a token-usage multiplier of 0.715, giving an effective cost of $0.3359 per 1M input + output tokens. That places it #8 of 117 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.

Cheaper Alternatives at Similar Capability

Models with a lower effective cost that score within a few IQ points of Gemma 4 31b (IQ 101), or better.

ModelProviderIQEffective Cost / 1M
gpt-oss-20bOpenAI100$0.1937
gemma-4-12bGoogle98$0.2859

Compare