Zumik
Sign inSign up

Llama 4 Scout Instruct (Basic)

Llama 4 Scout Instruct (Basic) on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout Fireworks AI
—
Input / 1M tokens
—
Output / 1M tokens
—
Cache read
1M
Context window

At a glance.

ProviderFireworks AI
Familyllama4_text
Released—
LicenseOpen weights
Context window1M tokens
Max output—
Parameters109B
Modalitiestext, image
Tool callingYes
Reasoning modeNo
Cachingnone
Batch discountNo batch tier

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for Llama 4 Scout Instruct (Basic) are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.

Same OpenAI client, this model.

python
from openai import OpenAI

client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")

r = client.responses.create(
    model="llama4-scout-instruct-basic",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Llama 4 Scout Instruct (Basic), answered.

How much does Llama 4 Scout Instruct (Basic) cost?

Llama 4 Scout Instruct (Basic) is an open-weights model routed through Fireworks AI. It is priced on the host's serverless size tier rather than a single published per-token list price, so it shows "—" here until profiled.

What is Llama 4 Scout Instruct (Basic)'s context window?

Llama 4 Scout Instruct (Basic) supports a 1M-token context window.

Run Llama 4 Scout Instruct (Basic) with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.

Migration quickstartBack to catalog