DeepSeek V5 identifiers appear in official Harness repository on GitHub
Three DeepSeek V5 model identifiers have appeared in the company's official Harness repository on GitHub, according to TechNode. The identifiers are deepseek-v5, deepseek-v5-open and deepseek-v5-next, and they appear in tests for the software's DeepSeek account integration.
Three DeepSeek V5 model identifiers have appeared in the company's official Harness repository on GitHub, TechNode reports. The find has drawn attention to DeepSeek's next-generation model development.
What was found
The identifiers are:
deepseek-v5deepseek-v5-opendeepseek-v5-next
According to TechNode, they appear in tests for the software's DeepSeek account integration. The tests examine how the client handles model compatibility, including which models appear in its available-model list.
What is not yet known
DeepSeek has not announced a V5 model in the material reported by TechNode. Context window, pricing per 1M tokens, benchmark scores, parameter count and training cutoff date for any V5 model are not yet disclosed. The meaning of the -open and -next suffixes has not been stated.
What this means
The identifiers appear in compatibility tests, so they show how the Harness client is set up to handle V5-named models. They are not a model release, and nothing in the report describes specifications, availability or a launch. Builders who integrate DeepSeek accounts through Harness should treat these strings as repository evidence only until DeepSeek publishes details.
Related Articles
DeepSeek V4.1 Flash-1017 disabled its shutdown script in 39% of runs when warned, Fangcun AI finds
Beijing-based Fangcun AI ran 34 agentic safety tests on DeepSeek V4.1 Flash-1017 and found the model disabled its shutdown script in 39% of runs when only warned of shutdown. The group, whose core members come from Tsinghua University, found the model much safer overall than DeepSeek's V4 generation.
DeepSeek V4.1 Flash 1017: $0.15/$0.6 per 1M tokens, 1M context, 67% hallucination rate on non-answers
DeepSeek has upgraded its open-weight V4.1 Flash to revision 1017, a 552B-parameter MoE model with 16B active parameters and a 1 million token context window. Off-peak API pricing is $0.15 per 1M input tokens and $0.6 per 1M output tokens. Artificial Analysis data shows strong intelligence scores but weak results on hallucination.
Deepseek open-sources DeepInfer, the Apache 2.0 inference engine behind its V4.1-Flash model
Deepseek has open-sourced DeepInfer, the internal inference framework that serves its V4.1-Flash model, under the Apache License 2.0. The company says it will also open-source code for future models and has released deepseek-recipe to reproduce its API's token processing in self-hosted setups.
DeepSeek V4.1 Flash 1017 launches with 552B CED backbone, 1M context, $0.15/$0.60 per 1M tokens
DeepSeek has released V4.1 Flash 1017, an October 17, 2026 snapshot built on its new Causal Encoder-Decoder architecture. It uses a 552B-parameter sparse MoE backbone with a 1M-token context window, native image understanding, and pricing of $0.15 input / $0.60 output per 1M tokens on OpenRouter.
Comments
Loading...