Fireworks AI · none caching
Llama Guard v2 8B
Llama Guard v2 8B on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
Specifications
At a glance.
| Provider | Fireworks AI |
| Family | llama |
| Released | — |
| License | Open weights |
| Context window | 8K tokens |
| Max output | — |
| Parameters | 8B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Llama Guard v2 8B 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.
Call it
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="llama-guard-2-8b",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Llama Guard v2 8B, answered.
How much does Llama Guard v2 8B cost?
Llama Guard v2 8B 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 Guard v2 8B's context window?
Llama Guard v2 8B supports a 8K-token context window.
Does Llama Guard v2 8B support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Llama Guard v2 8B shows a median cache capture of 76% on agent workloads.
Run Llama Guard v2 8B with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.