Gemma 3 4B
google/gemma-3-4b-it제공: Google · 패밀리: gemma · 출시 2025-03-13 · 지식 컷오프: 2024-10
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
기능
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding7
- Tool calling0/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability7/10
Agents12
- Tool calling0/35
- Structured output0/25
- Reasoning0/15
- Output token limit5/15
- Provider availability7/10
JSON / structured output30
- Structured output / JSON mode0/50
- Tool calling0/20
- Temperature control10/10
- Price-friendly for high-volume20/20
Cost efficiency100
- Headline price (log-scaled)95/95
- Has prompt-cache pricing5/5
Long context0
- Context ≥ 100K0/100
Vision75
- Accepts image input50/50
- Context window (10K → 1M)8/30
- Has published price10/10
- Provider availability7/10
Production-readiness89
- Number of independent providers35/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.06 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $0.13 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.03 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $0.11 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $0.14 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
가격 상세
추천 가격 제공자: chutes · unsloth/gemma-3-4b-it
가장 저렴한 제공자: google · Unknown 입력 + Unknown 출력
7곳 제공사에서 이용 가능
| 제공자 | 제공자 모델 ID | 입력 / 1M | 출력 / 1M | 컨텍스트 | 출시일 |
|---|---|---|---|---|---|
| Google google | gemma-3-4b-it | Unknown | Unknown | 33K | 2025-03-13 |
| Amazon Bedrock amazon-bedrock | google.gemma-3-4b-it | $0.040 | $0.080 | 128K | 2024-12-01 |
| OpenRouter openrouter | google/gemma-3-4b-it | $0.017 | $0.068 | 96K | 2025-03-13 |
| NanoGPT nano-gpt | unsloth/gemma-3-4b-it | $0.201 | $0.201 | 128K | 2025-03-10 |
| Chutes chutes | unsloth/gemma-3-4b-it | $0.010 | $0.027 | 96K | 2025-12-29 |
| Kilo Gateway kilo | google/gemma-3-4b-it | $0.040 | $0.080 | 131K | 2025-03-13 |
| LLM Gateway llmgateway | gemma-3-4b-it | Unknown | Unknown | 33K | 2025-03-13 |
제공자 간 데이터 불일치
- context_window varies: 128000, 131072, 32768, 96000
- release_date varies (span 393d): 2024-12-01, 2025-03-10, 2025-03-13, 2025-12-29
- modalities varies across offerings
제공자별로 이 모델의 값이 다릅니다. 위의 핵심 정보는 대표 제공자 기준이며, 제공자별 상세는 표를 참고하세요.
Frequently asked questions
How much does Gemma 3 4B cost?
Gemma 3 4B costs $0.010 per 1M input tokens and $0.027 per 1M output tokens, sourced from chutes. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Gemma 3 4B?
Gemma 3 4B has a context window of 33K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.
Does Gemma 3 4B support tool calling?
No. Gemma 3 4B does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.
Does Gemma 3 4B support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Gemma 3 4B in our data source. Verify with Google's official documentation before relying on it in production.
Can Gemma 3 4B accept image input?
Yes. Gemma 3 4B accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Google's docs for the exact rule.
Is Gemma 3 4B open-weight?
Yes. Gemma 3 4B's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Gemma 3 4B?
If Gemma 3 4B doesn't fit, consider Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3 Flash Preview. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Google models
- Gemini 2.5 Pro$1.25 in / $10.00 out
- Gemini 2.5 Flash$0.30 in / $2.50 out
- Gemini 3 Flash Preview$0.50 in / $3.00 out
- Gemma 3 27B$0.03 in / $0.11 out
- Gemini 3.1 Pro Preview$2.00 in / $12.00 out
Capability lists this model is in
마지막 업데이트:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.