Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Performance
The last 24 hours, all hosts combined. When one host fails, BazaarLink automatically routes to the next healthy one.
Hosts
Each host has its own price, and prices can differ between hosts. You can name a preferred host in your request.
| Host | Input /M | Output /M | Cache read /M | Cache write /M | First token | Throughput | Availability (24h) |
|---|---|---|---|---|---|---|---|
$0.05 | $0.10 | — | — | 0.84s | 74 tps | 100.0% |
Benchmarks
Price comparison
Input, output and cache usage of this model are all billed at BazaarLink's price.
BazaarLink price This site
Quick start
Just change base_url to use Gemma 3 4B through the BazaarLink API.
from openai import OpenAI
client = OpenAI(
base_url="https://api.bazaarlink.ai/v1",
api_key="sk-bl-YOUR_API_KEY",
)
response = client.chat.completions.create(
model="google/gemma-3-4b-it",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)FAQ
What is Gemma 3 4B?
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
How much does the Gemma 3 4B API cost?
Gemma 3 4B costs $0.05 per 1M input tokens and $0.10 per 1M output tokens when accessed through BazaarLink.
How do I use Gemma 3 4B with the OpenAI SDK?
Set base_url to "https://api.bazaarlink.ai/v1" and use model ID "google/gemma-3-4b-it". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.
What is the context window for Gemma 3 4B?
Gemma 3 4B supports a context window of 131,072 tokens.
Is Gemma 3 4B available for free?
Gemma 3 4B is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.
Explore
- Billed in USD with TWD quotes plus Taiwan e-invoices, so Taiwanese teams do not need an overseas card
- OpenAI-compatible API, no code rewrite
- When an upstream source has a problem, the request can try another available source; if none is available you get an error
- Chinese-language support from a local team