deepseek-r1 Benchmarks

Provider: together

Explore real-world latency and throughput results for deepseek-r1. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the together provider hub to compare every tracked model side-by-side.

Visit together Official Website

Benchmark Overview

Avg Tokens / Second

38.00

Avg Time to First Token (ms)

1770.00

Runs Analysed

238

Last Updated

Feb 8, 2026, 06:03 PM

Key Insights

  • deepseek-r1 streams at 38.00 tokens/second on average across the last 238 benchmark runs.

  • Performance fluctuated by 66.41 tokens/second (174.8% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 1770.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.

  • Latest measurements completed on Feb 8, 2026, 06:03 PM based on 238 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

Historical performance trends showing how throughput has changed over the benchmarking period.

deepseek-r1

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
togetherdeepseek-r138.001.0967.501770.00

Frequently Asked Questions

The latest rolling average throughput is 38.00 tokens per second with an average time to first token of 1770.00 ms across 238 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 06:03 PM.

Related Links