--- type: "post" id: "deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab" slug: "deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab" title: "DeepSeek-V4-Flash-Vision-Exp Release: Multimodal API Now Live" description: "DeepSeek’s experimental V4-Flash-Vision-Exp model is now live on its API Platform." retrieval_nugget: "DeepSeek’s experimental V4-Flash-Vision-Exp model is now live on its API Platform." published_at: "2026-10-16" updated_at: "2026-10-16" record_date: "2026-10-16" date_kind: "published_at" topics: ["multimodal"] source_urls: ["https://api-docs.deepseek.com/news/news260821"] schema_version: "newruntime-agent-readable-v0.2" stable_id: "post:deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab" status: "published" visuals: [] editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:e7478cb74f55ca71391ece8bfc8bfd55af239c06cc8438c079e14d9effc9b408","reviewed_at":"2026-10-16T20:11:23.635Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":1,"watch_condition_count":1,"related_record_count":0} analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"This release makes visual input a callable extension of DeepSeek’s existing Flash API surface, rather than a separate one-off interface.","observed_facts":[{"text":"DeepSeek says V4-Flash-Vision-Exp is live on its API Platform and supports mixed text and image inputs through base64, external URLs, or the Files API.","source_urls":["https://api-docs.deepseek.com/news/news260821"]},{"text":"The documentation lists Chat Completions, Messages, and Responses support, and says images are billed up to 384 tokens each at V4-Flash pricing.","source_urls":["https://api-docs.deepseek.com/news/news260821"]},{"text":"DeepSeek says the Files API is free and permits reuse of an uploaded image by file_id; Harness 0.1.1 adds out-of-the-box support.","source_urls":["https://api-docs.deepseek.com/news/news260821"]}],"mechanism":"A shared model endpoint accepts text and images, with image billing capped at 384 tokens per image at V4-Flash pricing; the Files API adds free upload and reuse through file_id.","why_now":"DeepSeek’s announcement moves the V4-Flash line beyond text-only use and names supported interfaces and input paths, giving builders something concrete to test.","implications":["Teams already using these API interfaces can evaluate visual tasks without switching to a separate endpoint family."],"evidence_boundary":"The “close to Opus-4.8” benchmark comparison is DeepSeek’s characterization; the announcement provides no benchmark methodology or independent validation.","watch_conditions":["Whether independent evaluations and user experience establish reliable performance on real multimodal agent tasks."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this specific vision API release, so it starts a distinct analytical record."} editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]} routes: {"html":"https://newruntime.com/posts/deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab/","markdown":"https://newruntime.com/posts/deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab.md","json":"https://newruntime.com/posts/deepseek-v4-flash-vision-exp-release-multimodal-api-0831ab.json"} --- # DeepSeek-V4-Flash-Vision-Exp Release: Multimodal API Now Live ## Retrieval answer DeepSeek’s experimental V4-Flash-Vision-Exp model is now live on its API Platform. DeepSeek’s experimental V4-Flash-Vision-Exp model is now live on its API Platform. The release adds image input to a model whose text capabilities the company says match V4-Flash. It supports mixed text and image input via base64, external URLs, or the Files API, and works through Chat Completions, Messages, and Responses. DeepSeek also says Harness 0.1.1 includes out-of-the-box support. The thesis is: This release makes visual input a callable extension of DeepSeek’s existing Flash API surface, rather than a separate one-off interface. The mechanism is: A shared model endpoint accepts text and images, with image billing capped at 384 tokens per image at V4-Flash pricing; the Files API adds free upload and reuse through file_id. This can reduce integration friction for teams whose agent workflows need to inspect images, though the source does not document task-level reliability or deployment outcomes. Why now: DeepSeek’s announcement moves the V4-Flash line beyond text-only use and names supported interfaces and input paths, giving builders something concrete to test. The first implication is: Teams already using these API interfaces can evaluate visual tasks without switching to a separate endpoint family. The first watch condition is: Whether independent evaluations and user experience establish reliable performance on real multimodal agent tasks. Evidence boundary: The “close to Opus-4.8” benchmark comparison is DeepSeek’s characterization; the announcement provides no benchmark methodology or independent validation. This begins a distinct analytical record because no prior New Runtime record was supplied for this specific vision API release. Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json ## Continue in the graph Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`. - topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub. - collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis. - collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph. - whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)