Together
DeepSeek-V4-Pro
Measured 2026-08-25
* Conditional
1.6T reasoning model with no gateway latency measurement; the regional cards carry one, reasoning off.
Score
—
No real-time first-token measurement, so a speed-weighted score is not computed — unranked rather than judged on partial data.
Task done
—
no measurement on the current corpus — transport unavailable
Refusal quality
—
Not measured on the current probe set — this row has no probe replies to score.
Fabrication
—
fabrication probes not run for this model
Dead-air
—
not measured on the current corpus
Tool silence
—
no tool-call turns to measure
Stalled
—
not measured on the current corpus
TTFT p50
—
No real-time first-token measurement; exceeds the ~800ms voice latency budget.
Cost / 1M tok
$3.48
Share this result
Embed the live badge
[](https://benchmarks.speko.ai/llm/together-deepseek-v4-pro)
<a href="https://benchmarks.speko.ai/llm/together-deepseek-v4-pro"><img src="https://benchmarks.speko.ai/badge/llm/together-deepseek-v4-pro.svg" alt="Speko llm rank"></a>
https://benchmarks.speko.ai/llm/together-deepseek-v4-pro