Fireworks AI · none caching
Qwen QWQ 32B Preview
Qwen QWQ 32B Preview 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 | qwen2 |
| Released | — |
| License | Open weights |
| Context window | 33K tokens |
| Max output | — |
| Parameters | 33B |
| Modalities | text |
| Tool calling | No |
| Reasoning mode | Yes |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Qwen QWQ 32B Preview 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="qwen-qwq-32b-preview",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Qwen QWQ 32B Preview, answered.
How much does Qwen QWQ 32B Preview cost?
Qwen QWQ 32B Preview 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 Qwen QWQ 32B Preview's context window?
Qwen QWQ 32B Preview supports a 33K-token context window.
Does Qwen QWQ 32B Preview support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Qwen QWQ 32B Preview shows a median cache capture of 77% on agent workloads.
Run Qwen QWQ 32B Preview with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.