Skip to content
models / Meta / Llama 3.3 70B Instruct FP8 Fast

Llama 3.3 70B Instruct FP8 Fast

textmeta/llama-3.3-70b-instruct-fp8-fastZDR supported

Llama 3.3 70B quantized to fp8 precision, optimized to be faster.

$2.25list priceper 1M output tokens
pricing
unitlist price
per 1M input tokens$0.293
per 1M output tokens$2.25

Everyone pays the list price. What comes back grows with your Reward Status: Noob 0.5% of every spend buys back $INFX, Pro (hold 1,337 $INFX) 2%, Elite (also hold 1,337 $XAVA) 5%. How it works

openai sdk (python)
from openai import OpenAI

client = OpenAI(
    base_url="https://xavainf.com/v1",
    api_key="xk_live_...",  # your Xava Inference key
)

r = client.chat.completions.create(
    model="meta/llama-3.3-70b-instruct-fp8-fast",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)
curl
curl https://xavainf.com/v1/chat/completions \
  -H "Authorization: Bearer $XINF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/llama-3.3-70b-instruct-fp8-fast","messages":[{"role":"user","content":"Hello!"}]}'
limits
providerMeta
typetext
context window24,000 tokens
max output—
prompt storagenone
provider retentionnone ZDR supported
livesoon
requests 24h—
p50 latency—
uptime 7d—