DeepSeek V4.1 Flash hands-on tests and comparisons

Summarizes DeepSeek's own numbers: 77.0 on DeepSWE v1.1 versus 74.2 before, 74.0 for Opus 5 and 73.0 for Sol, while Opus 5 still leads HLE and Terminal-Bench; MIT weights, unchanged API pricing, Search/Fetch at $0.75 per 1,000 calls.

Web and app updated with API still on deepseek-flash at unchanged price; lists HLE 42.6, Terminal-Bench 4.0 42.3, DeepSWE v1.1 77.0 and says runtime and output length are shorter.

A user generated an SVG camera with DeepSeek V4.1-Flash-1017 inside DeepSeek Harness, saying the result looks like it was routed to Sonnet 5.5.

DeepSeek launched its AI-oriented search API and rolled out V4.1-Flash 1017 across web, app and API with unchanged naming and pricing.

Official release: stronger performance and shorter outputs, live on web, app and API, with open weights and a new Search & Fetch API plus Harness and CodeBuddy tuning.

Release roundup: Terminal-Bench 4.0 rises 31.2 to 42.3, HLE 36.8 to 42.6, programBench 20.3 to 29.1, DeepSWE hits 77.0 ahead of Opus 5 and GPT 5.6 Sol, API price unchanged, live on web and app.

A deepseek-v4.1-flash call returns a new system_fingerprint matching the 1017 build, with routing_info and X-Ds-Trace-Id showing direct official API passthrough, so client model IDs stay unchanged.

A post says V4.1 Flash is free with unlimited usage in the OpenCode desktop app on macOS and Windows, with no subscription or API cost.

Experts are losslessly transcoded from MXFP4 to NVFP4 at about 430GB, fitting on four DGX Sparks with roughly 80GB left for KV cache, with a two-Spark build reportedly in the works.

Running the classic pelican-on-a-bicycle prompt through Codex and DeepSeek Harness produced an animated SVG turned into an 11-second video, using ~2.87M tokens at 92% cache hit rate for roughly one yuan.

Release roundup: upgraded one-sentence-to-full-project coding, web/app/API updated at the same price with open weights; the author plans to test it hands-on.

Official release: MIT-licensed open weights, with vendor-run evals showing Terminal-Bench 4.0 rising from 31.2 to 42.3 and Apex Bench from 64.6 to 72.1.