DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.
At a glance.
| Provider | Fireworks AI |
| Family | deepseek_v3 |
| Released | — |
| License | Open weights |
| Context window | 164K tokens |
| Max output | — |
| Parameters | 674B |
| Modalities | text |
| Tool calling | Yes |
| Reasoning mode | Yes |
| Caching | none |
| Batch discount | No batch tier |
What reuse looks like here.
Pricing, context, and capabilities for DeepSeek V3.1 Terminus 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="deepseek-v3p1-terminus",
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseDeepSeek V3.1 Terminus, answered.
How much does DeepSeek V3.1 Terminus cost?
DeepSeek V3.1 Terminus 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 DeepSeek V3.1 Terminus's context window?
DeepSeek V3.1 Terminus supports a 164K-token context window.
Run DeepSeek V3.1 Terminus with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.