DeepSeek officially launched deepseek-v4-flash and deepseek-v4-pro in preview on April 24, 2026. The legacy routes (deepseek-chat, deepseek-reasoner) are deprecated July 24, 2026.

I’ve been thinking through how to actually structure a routing decision around this, and wanted to share a few observations:

The key trade-off is not “DeepSeek vs Claude/GPT” — it’s “which tier for which workload.”

Flash at $0.14/$0.28 per 1M tokens is a serious candidate for coding agents, repo analysis, and long-context summarization. Pro at $1.74/$3.48 sits between Flash and the premium tier.

The question I’d be asking: what percentage of your current workloads could Flash handle without quality regression? For many teams doing code gen and repo reading, the answer might be 60-80%. That’s a meaningful cost change.

The caveat: V4 is preview. Reuters used that word explicitly. Run your own eval set before committing to routing changes, and keep rollback paths to your existing premium routes.

Has anyone already run Flash or Pro against production workloads? Curious what failure modes you’ve seen, if any. The tool-call reliability question is the one I’m most uncertain about.