Llama 4 Maverick 17B 128E Instruct FP8 API
Run meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
Llama 4 Maverick 17B 128E Instruct FP8 pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | $0.21 |
| Output | $0.84 |
Served by 1 provider
Requests route to DeepInfra by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| deepinfra | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
Call Llama 4 Maverick 17B 128E Instruct FP8 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="meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
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": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"messages": [{"role": "user", "content": "Hello!"}]
}'Llama 4 Maverick 17B 128E Instruct FP8 — common questions
How much does the meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 API cost?
On FastInfra, meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 costs $0.21/1M input, $0.84/1M output tokens. Billing is per token used, with no subscription.
Is meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 compatible with the OpenAI SDK?
Yes. FastInfra exposes meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 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 meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8?
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 is available from 1 provider(s): deepinfra. Requests route to DeepInfra by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: Llama 4 Maverick 17B 128E Instruct FP8 vs Llama3.1:8b · Llama 4 Maverick 17B 128E Instruct FP8 vs Llama3.2:1b · Llama 4 Maverick 17B 128E Instruct FP8 vs Llama3.2:3b