deepseek ai-gateway agent-benchmarks inference vercel

DeepSeek V4 Flash weights update ships on AI Gateway

V4 Flash now routes updated weights by default—Terminal-Bench score jumps 25.8 points to 82.7—no code changes required.

Summary

Agentic capabilities improve significantly without migration friction; code agents targeting `deepseek/deepseek-v4-flash` automatically get the stronger model. Matters for developers running inference agents on constrained budgets or latency targets.

Why it matters

Implementation verdict

Drop-in replacement for existing V4 Flash calls. Requires only setting `model: 'deepseek/deepseek-v4-flash'` in AI SDK or agent config. Worth trying now if you're already on DeepSeek; other providers with updated weights ship next week. Zero Data Retention option incoming.

Sources

1.DeepSeek V4 Flash now runs on updated weights by default on AI Gateway, with notably stronger agentic capabilities
2.On Terminal-Bench, it scores 82.7, up 25.8 points from 56.9 in the April preview
3.Requests to `deepseek/deepseek-v4-flash` pick up the new weights automatically, with no change to the model ID or your code
4.For now, DeepSeek is the only provider serving the updated weights. Other providers, including ones with Zero Data Retention, are coming next week

Dev Signal

Get briefs like this in your inbox — free, every weekday.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.

Read the full issue →All briefs