DeepSeek V4.1 Flash 1017
LabsDeepSeek V4.1 Flash 1017 as a Labs experiment, open for a short test window: temporary, not a permanent id.
- Price per 1M tokens
- Free
- With a Labs seat until October 20, 2026
- Context
- 1M
- 384K max output
- Vision
- Tool calling
- Reasoning optional, default high
How it ranks
Against every model we serve, best first. Starred scores are reported by the publisher on its model card; the rest are independent measurements. About the scores
- GLM 5.345
- Kimi K344
- GLM 5.3 Flash42
- DeepSeek V4.1 Flash39
- DeepSeek V4 Flash34
- Qwen3.6 35B A3B18
Not published: DeepSeek V4.1 Flash 1017.
- DeepSeek V4.1 Flash 1017 (Labs)77%* reported by the publisher
- DeepSeek V4.1 Flash74.2%* reported by the publisher
- GLM 5.369%
- Kimi K368.5%
- GLM 5.3 Flash63.4%
- DeepSeek V4 Flash54.4%* reported by the publisher
Not published: Qwen3.6 35B A3B.
- DeepSeek V4.1 Flash90.6%* reported by the publisher
- Kimi K385%
- GLM 5.3 Flash84.3%
- GLM 5.383.9%
- DeepSeek V4 Flash78.7%
- Qwen3.6 35B A3B44.9%
Not published: DeepSeek V4.1 Flash 1017.
- DeepSWE for DeepSeek V4.1 Flash 1017: reported by the publisher on its model card. Source
Pricing
Free with a Labs seat until October 20, 2026. Seats are limited and rotate, and an experiment is not meant for production work.
Specs
- Context window
- 1M tokens
- Max output
- 384K tokens
- Vision
- Yes
- Tool calling
- Yes
- Reasoning
- Adjustable (none, low, high, max)
- Default effort
- high
- Weights
- FP8 on Hugging Face
- Stage
- Labs experiment
Quickstart
Pick your tool; the command already carries this model's id. Calls need a Labs seat on your account while the experiment runs. More tools (Pi, Copilot, Zed, omp) in the setup guides.
OpenCode
Built inLaunch OpenCode on this model with the umans CLI. Umans AI is also built into OpenCode: run /connect and pick it.
curl -fsSL https://api.code.umans.ai/cli/install.sh | bash # once
umans opencode --model umans-deepseek-v4.1-flash-1017-labOr consider
- DeepSeek V4.1 Flash$0.15 in · $0.60 out per 1MBest for fast agentic coding at a low price.DeepSWE 74.2%* reported by the publisher
- GLM 5.3$1.40 in · $4.40 out per 1MBest for complex, long-horizon coding.DeepSWE 69%
- Kimi K3$3.00 in · $15.00 out per 1MBest for the hardest, highest-stakes tasks.DeepSWE 68.5%