Gemma 3 4B with Jev
Gemma 3 4B is a model from Google, released 2025-03-13. It costs $0.050 per million input tokens and $0.100 per million output tokens, reads up to 131K tokens of context, and writes up to 16,384 tokens in one reply. Through llm11, set model to google/gemma-3-4b-it.
- Input price
- $0.050 / 1M
- Output price
- $0.100 / 1M
- Context window
- 131K tokens
- Max output
- 16K tokens
- Released
- 2025-03-13
- Accepts
- text, image
Read from the live catalogue and refreshed daily. At blended list price, 96% of the 332 priced models we can call cost more.
Using Gemma 3 4B with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Gemma 3 4B does the answering when Jev sends it work, or when you name it yourself. Gemma 3 4B falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
Jev is new, so we have not published results for Gemma 3 4B with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00004 | $0.045 |
| Question over retrieved documents | 4,000 / 500 | $0.00025 | $0.250 |
| Long document summary | 30,000 / 1,000 | $0.00160 | $1.60 |
Cheaper models to try
The catalogue has no benchmark score for Gemma 3 4B, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Mistral Small 3 | $0.050 | $0.080 | 33K | |
| Meta Llama 3.1 8B Instruct | $0.050 | $0.080 | 131K | |
| Qwen Qwen3.7 Flash | $0.030 | $0.130 | 1M | |
| OpenAI gpt-oss-20b | $0.018 | $0.090 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="google/gemma-3-4b-it",
messages=[{"role": "user", "content": "Hello"}],
)More from Google
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Gemini 3.8 Flash | $0.750 | $3.75 | 1.05M | |
| Gemini 3.7 Flash | $0.750 | $3.75 | 1.05M | |
| Gemini 3.5 Flash Lite | $0.300 | $2.50 | 1.05M | |
| Gemini 3.6 Flash | $0.750 | $3.75 | 1.05M | |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1.05M | |
| Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1.05M |
Questions
- What is Gemma 3 4B with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Gemma 3 4B does the answering when Jev sends it work, or when you name it yourself. Gemma 3 4B falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Gemma 3 4B a System One model?
- No. Gemma 3 4B answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Gemma 3 4B cost?
- $0.050 per million input tokens and $0.100 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00025, so a thousand of them is about $0.250. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Gemma 3 4B context window?
- 131,072 tokens, with up to 16,384 tokens in a single reply.
- Does Gemma 3 4B support tool calling and structured output?
- The catalogue lists structured output, but it does not list tool calling and reasoning controls.
- Can I use Gemma 3 4B through llm11?
- Yes. Set model to google/gemma-3-4b-it on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Gemma 3 4B?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Gemma 3 4B falls in the llm11-fast band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
- What is a cheaper alternative to Gemma 3 4B?
- Nearest in price and below it: Mistral Mistral Small 3 at $0.050 in and $0.080 out, Meta Llama 3.1 8B Instruct at $0.050 in and $0.080 out and Qwen Qwen3.7 Flash at $0.030 in and $0.130 out. The catalogue has no benchmark score for Gemma 3 4B, so this is a price ordering. It does not claim these answer as well.