Gemma 3 4B
$0.04 per 1M input tokens and $0.05 per 1M output tokens · 131K context · vision, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Gemma 3 4B costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $14.28 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $3.79 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $10.20 |
| Content generation 30 long articles a day | $0.221 |
| Classification / extraction 100,000 short items a day | $38.25 |
Price history
We started tracking Gemma 3 4B on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Gemma 3 4B: 2 providers
Parasail is the cheapest at $0.04 input / $0.05 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
Cheaper alternatives to Gemma 3 4B
Models with the same image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Lyria 3 Clip Preview | $0 | $0 | 1.05M | visionJSON |
| Lyria 3 Pro Preview | $0 | $0 | 1.05M | visionJSON |
How to pay less for Gemma 3 4B
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $18.60 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Lyria 3 Clip Preview (similar capabilities) | $0 | $18.60 (100%) |
| Use prompt caching (60% of input cached) | $14.28 | $4.32 (23%) |
Other workloads: cut-your-bill tool for Gemma 3 4B.
Specifications
| Model ID | google/gemma-3-4b-it |
| Input | text, image |
| Output | text |
| Tool calling | No |
| Structured output | Yes |
| Reasoning mode | No |
| Open weights | Yes — google/gemma-3-4b-it |
| Knowledge cutoff | 2024-08-31 |
| Released | Mar 13, 2025 |
FAQ
- How much does Gemma 3 4B cost?
- $0.04 per million input tokens and $0.05 per million output tokens; cached input costs $0.02 per million. Prices as of Oct 21, 2026.
- What is the context window of Gemma 3 4B?
- 131K tokens, with up to 118K output tokens per response.
- Does Gemma 3 4B support images, tools and structured output?
- Images as input: yes. Tool calling: no. Structured (JSON) output: yes. Reasoning mode: no.
- What are cheaper alternatives to Gemma 3 4B?
- Models with the same key capabilities for at least 20% less include Lyria 3 Clip Preview ($0 / $0), Lyria 3 Pro Preview ($0 / $0).
More from Google: all Google models · how we collect prices