Fireworks AI · none caching
Qwen3.5 397B A17B
Qwen3.5 397B A17B 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 | qwen3_5_moe |
| Released | — |
| License | Open weights |
| Context window | 262K tokens |
| Max output | — |
| Parameters | 397B |
| Modalities | text, image |
| Tool calling | Yes |
| Reasoning mode | Yes |
| Caching | none |
| Batch discount | No batch tier |
Measured by Zumik
What reuse looks like here.
Pricing, context, and capabilities for Qwen3.5 397B A17B 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="qwen3p5-397b-a17b",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseFrequently asked
Qwen3.5 397B A17B, answered.
How much does Qwen3.5 397B A17B cost?
Qwen3.5 397B A17B 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 Qwen3.5 397B A17B's context window?
Qwen3.5 397B A17B supports a 262K-token context window.
Does Qwen3.5 397B A17B support prompt caching?
Yes. Fireworks AI uses Automatic prompt caching (serverless and dedicated) caching. In the Zumik corpus, Qwen3.5 397B A17B shows a median cache capture of 80% on agent workloads.
Run Qwen3.5 397B A17B with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.