Qwen3-VL-8B-Instruct
Qwen3-VL-8B-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 | qwen3_vl |
| Released | 2025-10 |
| License | Open weights |
| Context window | 131K tokens |
| Max output | 33K tokens |
| Parameters | 9B |
| Modalities | text, image, video |
| Tool calling | Yes |
| Reasoning mode | No |
| Caching | none |
| Batch discount | No batch tier |
What reuse looks like here.
Pricing, context, and capabilities for Qwen3-VL-8B-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.
What you actually pay once caching works.
At a typical 55% prefix reuse, a million input tokens on Qwen3-VL-8B-Instruct effectively costs $0.08 instead of $0.08 - blending to roughly $0.18 with a 25% output share. There is no batch tier, so cost control here leans on caching and routing.
Estimate it for your workloadRoute it directly by id, or let an alias pick it when it wins under policy.
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="qwen3-vl-8b-instruct",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseQwen3-VL-8B-Instruct, answered.
How much does Qwen3-VL-8B-Instruct cost?
Qwen3-VL-8B-Instruct is $0.08 per million input tokens and $0.50 per million output tokens through Zumik. Cache reads are $0.08 per million, a 0% discount on input.
What is Qwen3-VL-8B-Instruct's context window?
Qwen3-VL-8B-Instruct supports a 131K-token context window with up to 33K output tokens.
Run Qwen3-VL-8B-Instruct with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.