Models / Chat / Marin 8B Instruct API
Marin 8B Instruct API
Chat
8B open-source SFT-only LLM using Llama architecture, trained on diverse high-quality academic and code datasets.
Try our Marin API

New
Marin 8B Instruct API Usage
Endpoint
marin-community/marin-8b-instruct
RUN INFERENCE
curl -X POST "https://api.together.xyz/v1/chat/completions" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "marin-community/marin-8b-instruct",
"messages": [],
"stream": true
}'
RUN INFERENCE
from together import Together
client = Together()
response = client.chat.completions.create(
model="marin-community/marin-8b-instruct",
messages=[],
stream=True
)
for token in response:
if hasattr(token, 'choices'):
print(token.choices[0].delta.content, end='', flush=True)
RUN INFERENCE
import Together from "together-ai";
const together = new Together();
const response = await together.chat.completions.create({
messages: [],
model: "marin-community/marin-8b-instruct",
stream: true
});
for await (const token of response) {
console.log(token.choices[0]?.delta?.content)
}
How to use Marin 8B Instruct
Model details
Prompting Marin 8B Instruct
Applications & Use Cases
Model Provider:
Marin Community
Type:
Chat
Variant:
Parameters:
8B
Deployment:
✔ Serverless
✔ On-Demand Dedicated
✔ Monthly Reserved
Quantization
FP16
Context length:
131072
Pricing:
$0.18
Check pricing
Run in playground
Deploy model
Quickstart docs
Quickstart docs
Serverless
Monthly Reserved
Looking for production scale? Deploy on a dedicated endpoint
Deploy Marin 8B Instruct on a dedicated endpoint with custom hardware configuration, as many instances as you need, and auto-scaling.
