Phi-3 Mini 128k Instruct
Phi-3 Mini 128k Instruct on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
At a glance.
| Provider | Fireworks AI |
| Family | phi |
| Released | — |
| License | Open weights |
| Context window | 131K tokens |
| Max output | — |
| Parameters | 4B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
What reuse looks like here.
Pricing, context, and capabilities for Phi-3 Mini 128k Instruct 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.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="phi-3-mini-128k-instruct",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reusePhi-3 Mini 128k Instruct, answered.
How much does Phi-3 Mini 128k Instruct cost?
Phi-3 Mini 128k Instruct 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 Phi-3 Mini 128k Instruct's context window?
Phi-3 Mini 128k Instruct supports a 131K-token context window.
Run Phi-3 Mini 128k Instruct with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.