DeepSeek V4.1 Flash hands-on tests and comparisons

OpenCode says DeepSeek V4.1 Flash 1017 is now free to use in its coding tool, with no further details given.

A Japanese hands-on reports 99% cache hit on the first turn, over 200 tok/s, and that the model can be jailbroken.

The poster says the 552B MoE V4.1-flash-1017 beats Opus 5 on DeepSWE and Automation-Bench while costing $1.20/M output tokens ($0.60 off-peak), over 20x cheaper.

An English post relays the official update: stronger coding, 3D, visual understanding and agent workflows, shorter and faster outputs, and a 1M-token context at unchanged API pricing, though the author has not tested it yet.

Terminal-Bench 4.0 rose 31.2 to 42.3, ProgramBench 20.3 to 29.1 and DeepSWE v1.1 74.2 to 77.0, above GPT-5.6 Sol's 73.0 and Opus 5's 74.0, with shorter task time and output; the author cautions against calling it a total sweep.

The poster argues 1017 is a brand-new version rather than a minor update, comparing its wish-granting coding feel to Opus 5.5 and Fable 5.1.

Official charts show Terminal-Bench 4.0 rising from 31.2% to 42.3% and DeepSWE at 77.0%, with unchanged API pricing, shorter outputs and MIT open weights already live.

Official charts put it at 77.0% on DeepSWE v1.1, above Opus 5's 74.0 and GPT-5.6-Sol's 73.0, while still trailing Opus 5 on HLE and ProgramBench; top tier costs about $0.2 per task.

Scanning OpenCode's pricing table turns up 15 models free on both input and output, with DeepSeek V4.1 Flash, GLM 5.3 Flash and Reflection Beam highlighted; Beam's free tier excludes mainland China, Hong Kong and Macau and retains data for 30 days.

Per OpenRouter, the model has a 552B backbone with 8B active when reading and 16B when writing, input priced at $0.0284 per million tokens; the author questions whether real workloads use the 1M context.

The poster claims DeepSeek V4.1 Flash 1017 performs near GPT-6.1 Sol xHigh while priced like GPT-6 Luna, putting OpenAI in a bad spot.

A user says deepseek-v4.1-flash-1017 has better benchmarks, shorter answers and fewer tokens per task, making each finished task cheaper.