Google Gemma 3 4B: price cut input $0.050 → $0.040 per 1M tokens (-20 %), output $0.100 → $0.050 per 1M tokens (-50 %)
On the listed price of Google Gemma 3 4B changed: input $0.050 → $0.040 per 1M tokens (-20 %); output $0.100 → $0.050 per 1M tokens (-50 %). A later check on confirmed it. Prices as listed in the United States.
What changed
Google Gemma 3 4B is cheaper on OpenRouter. Source: price page as read.
What it does to a task
Standard tasks, visible output only, no cache discount; month = 20 tasks an hour around the clock.
| Task | Per task, before | Per task, now | Per month, before | Per month, now |
|---|---|---|---|---|
| L1 · Micro-task (classification or strict JSON extraction) | $0.0001 | $0.0001 | $1.39 | $1.02 |
| L2 · Deep analysis over a 50,000-token document | $0.0083 | $0.0065 | $120.45 | $95.05 |
| L3 · Agentic coding loop, 15 steps | $0.067 | $0.053 | $973.45 | $774.82 |
Same task on other models
The L2 task on other models we follow closely, at today's prices:
- Anthropic: Claude Haiku 5.5 — $0.017 per L2 task
- DeepSeek: DeepSeek V4.1 Flash 1017 — $0.051 per L2 task
Recalculate for your workload
Open the task cost calculator with this model and your own numbers. Model card with the full price history