isoquant
Day 16 after signup
DeepSeek V4.1 Flash 1017 runs at 600+ tok/s on Isoquant
Why it works
- Lead with the new capability and its clearest performance claim so readers understand the announcement immediately.
- Follow headline metrics with pricing and practical setup instructions to make the update useful, not just exciting.
- Keep the call to action focused on trying the capability with an existing account or API key.
How it is built
- Personal greeting
- Model launch announcement
- Performance and pricing details
- API setup instructions
Email copy
Hi [First name], we’ve launched DeepSeek V4.1 Flash 1017 Fast on Isoquant, reaching 600+ tokens per second for reasoning, coding, and vision. This is our AI optimizing AI, and we are passing performance wins and cost savings on to you: → 0.24s P50 / 1.16s P95 time to first token → about 3× standard output speed → $0.035 input / $0.005 cached / $0.37 output per 1M tokens Keep your code and harness. Use your existing Isoquant API key and select deepseek-v4.1-flash-1017-fast No waitlist, live now: https://console.isoquant.ai/ Aniket Co-founder, Isoquant