DeepSeek-V4-Flash-Vision-Exp is live on the API: it matches V4-Flash on text—including agents, reasoning, and world knowledge—while jumping on multimodal agent benchmarks to near Claude Opus 4.8. A free Files API and DeepSeek Harness 0.1.1 ship with it; images bill at V4-Flash rates (up to 384 tokens each) and drop into existing agent frameworks.

Key Takeaways

  • ✓The experimental vision model keeps V4-Flash text/agent strength while pushing multimodal agent scores close to Opus 4.8
  • ✓Chat Completions, Messages, and Responses are supported; images mix in via base64, URLs, or the Files API
  • ✓Files API is free with file_id reuse, and Harness 0.1.1 supports the model out of the box for agent stacks
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
The experimental vision model keeps V4-Flash text/agent strength while pushing multimodal agent scores close to Opus 4.8
Full Leaderboard→
💰 Cost & PlansCompare
in: $0.14 / out: $0.28
Compare Plans↗
🛠️ Ecosystem & IDERules
AI · LLM · Multimodal
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextDeepSeek Ships V4-Flash-Vision-Exp, Nearing Opus 4.8 on Multimodal Agents
Read Now→