Fireworks AI · none caching
Zephyr 7B Beta
Zephyr 7B Beta 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 | mistral |
| Released | — |
| License | Open weights |
| Context window | 33K tokens |
| Max output | — |
| Parameters | 7B |
| 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 Zephyr 7B Beta 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="zephyr-7b-beta",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Zephyr 7B Beta, answered.
How much does Zephyr 7B Beta cost?
Zephyr 7B Beta 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 Zephyr 7B Beta's context window?
Zephyr 7B Beta supports a 33K-token context window.
Does Zephyr 7B Beta support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Zephyr 7B Beta shows a median cache capture of 72% on agent workloads.
Run Zephyr 7B Beta with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.