DeepSeek has released an experimental vision model that combines image understanding with its V4-Flash text capabilities.
On internal benchmarks, it nearly matches Anthropic's Opus 4.8 on agent tasks.
The model works with OpenAI and Anthropic APIs and handles multiple image formats up to 8,192 pixels per side.
What happened
Chinese AI company DeepSeek released V4-Flash-Vision-Exp, an experimental multimodal model that adds image understanding to its text capabilities. On DeepSeek's internal multimodal agent benchmarks, the model scores close to Opus 4.8.
Why it matters
DeepSeek-V4-Flash-Vision-Exp extends the base text model while preserving its reasoning and world knowledge performance. The vision variant is designed for agent-based applications—it can describe images, extract text from screenshots, analyze diagrams, and work with OpenAI's Chat Completions and Responses APIs as well as Anthropic's Messages endpoint.
What to watch
Developers can send images three ways—Base64 encoding, publicly accessible URLs (up to 32 MiB), or DeepSeek's free Files API (64 MiB limit). A single request supports up to 600 images; each image costs at most 384 tokens, and pricing follows V4-Flash rates. DeepSeek also released version 0.1.1 of its Harness framework, which supports the new model out of the box.
Ask the AI about this article →
DeepSeek-V4-Flash-Vision-Exp represents the company's push into multimodal agent workflows, extending its existing V4-Flash model with vision capabilities while maintaining the base model's text performance in reasoning and world knowledge. The model's near-parity with Opus 4.8 on DeepSeek's internal multimodal agent benchmarks suggests competitive positioning in the visual reasoning space. The compatibility with both OpenAI's and Anthropic's APIs—Chat Completions, Responses APIs, and the Messages endpoint—signals that DeepSeek is designed for integration into existing workflows rather than as a standalone alternative. The release of version 0.1.1 of DeepSeek's Harness framework with out-of-the-box support for the new model underscores the company's investment in developer tooling and ecosystem development.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Palo Alto Networks' Unit 42 expanded its Frontier AI Exposure Analysis service by integrating Anthropic's Clau…
SpaceXAI released Grok 4.6—its latest flagship model—on Google Cloud's Vertex AI platform on August 21, 2026…
PepsiCo's sustainability team has restructured how it publishes environmental and social data, moving away fro…
Google Cloud announced Grok 4.6, its latest flagship model, is now available on Vertex AI through Model Garden
Salesforce reported $11.13 billion in revenue (up 13%) with Agentforce and Data 360 reaching $3.4 billion in A…
SpaceX's AI division has launched Grok 4.6, its latest large language model, on Google Cloud's Vertex AI platf…
