Llama 3.1 8B Instruct

Llama 3.1 8B Instruct is Meta's small-form-factor flagship from the 3.1 family, a dense 8B parameter model fine-tuned for instruction following, with 128K context and broad multilingual coverage. Best fit: high-volume backend traffic, classification, simple agent loops, and any workload where per-token cost dominates quality requirements. Pair with a stronger flagship for fall-back routing.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="meta-llama/llama-3.1-8b-instruct",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)