llm-benchmarks
githubdrose.io

ionstream Provider Benchmarks


Measured over the last 30 days

Models Tracked
1
Avg Tokens / Second
28.10
Avg Time to First Token (ms)
1250.00
Last Updated
Oct 22, 2026

All ionstream models

1 live · one row per model · fastest first · 1 folded behind their current lane
ModelAvg Toks/SecMinMaxAvg TTF (ms)
DeepSeek V4 Pro 081328.1011.9051.601250.00

Frequently Asked Questions

Which ionstream model is fastest?
Based on recent tests, DeepSeek V4 Pro 0813 shows the highest average throughput among tracked ionstream models.
How many recent measurements feed this dashboard?
This provider summary aggregates 85 individual prompts measured across 85 monitoring runs over the past month.