Meta Llama 3.1 8B Instruct AWQ INT4 API
Run togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
Meta Llama 3.1 8B Instruct AWQ INT4 pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | — |
| Output | — |
Served by 1 provider
Requests route to Together AI by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| together | togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 |
Call Meta Llama 3.1 8B Instruct AWQ INT4 in 30 seconds
Works with any OpenAI SDK — change the base URL and API key only.
Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")
response = client.chat.completions.create(
model="togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl
curl https://api.fastinfra.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4",
"messages": [{"role": "user", "content": "Hello!"}]
}'Meta Llama 3.1 8B Instruct AWQ INT4 — common questions
How much does the togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 API cost?
On FastInfra, togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 costs Pay-per-token pricing via provider routing. Billing is per token used, with no subscription.
Is togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 compatible with the OpenAI SDK?
Yes. FastInfra exposes togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.
Which providers serve togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4?
togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4 is available from 1 provider(s): together. Requests route to Together AI by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: Meta Llama 3.1 8B Instruct AWQ INT4 vs All Minilm · Meta Llama 3.1 8B Instruct AWQ INT4 vs Deepseek Coder:1.3b · Meta Llama 3.1 8B Instruct AWQ INT4 vs Gemma2:2b