Gemma 4 31B API Pricing
Google · context window 262K · prices updated 2026-09-15
Where Gemma 4 31B sits on price
At $0.34 per million output tokens, Gemma 4 31B is a budget tier model — 6.1× cheaper than the median output price of $2.08, which puts it cheaper than 85% and pricier than 15% of the models we track. It sits 5th cheapest of the 38 Google models we track. Output costs 3.8× input, the usual spread — trim both, starting with the answer length.
Cached input is 44% cheaper. On an input-heavy workload you need roughly a 57% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Gemma 4 31B
These three workloads are the ones teams actually run on a budget-priced model — a $0.34/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. | $0 | $257 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0001 | $2.88 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0004 | $132 |
Model your exact traffic in the API cost calculator — it preloads Gemma 4 31B with caching and batch options.
Gemma 4 31B price history
Google last raised Gemma 4 31B's output price on Aug 26, 2026, from $0.1/$0.34 to $0.09/$0.34 per 1M in/out. That is the only repricing in the 44 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $0.1 | $0.34 | — |
| Aug 26, 2026 | $0.09 | $0.34 | 0% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Gemma 4 31B vs Qwen3 235B A22B Instruct 2507
The closest-priced alternative from another vendor is Qwen3 235B A22B Instruct 2507 (Alibaba (Qwen)) — 3% more expensive on output, with $0.0025 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen3 235B A22B Instruct 2507 pricing →Cheaper alternatives
More Google models
Frequently asked questions
› How much does the Gemma 4 31B API cost?
Gemma 4 31B costs $0.09 per million input tokens and $0.34 per million output tokens, with cached input at $0.05 per million (44% cheaper). That works out to roughly 2,941,176 output tokens per dollar.
› What does the high-volume classification workload cost on Gemma 4 31B?
High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $257 per month on Gemma 4 31B. Short output, huge volume: the input price dominates the bill.
› What does it cost to fill Gemma 4 31B's 262K context window?
Sending 262K of input in a single request costs $0.0236 at $0.09 per million tokens — before any output. With prompt caching that same fill drops to about $0.0131 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Gemma 4 31B worth the price?
Gemma 4 31B is in the cheapest end of the market — cheaper than 85% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.