AI posts
AI release notes
DeepSeek's official news page: new DeepSeek models and changes for developers.
Compiled by the Toolstash team · Updated
DeepSeek API
Opening up the in-house search API
DeepSeek's web and API search capabilities are powered by our in-house DeepSeek search engine, which reliably handles hundreds of millions of search requests from around the world every day. DeepSeek Search is an AI-native general-purpose search engine that indexes hundreds of billions of web pages, supports multilingual search, and returns highly relevant, authoritative, and timely results in real time. It filters SEO spam, GEO manipulation, and low-quality AIGC through strict detection mechanisms, ensuring authoritative and trustworthy information for users and LLMs. For usage details, see the Search & Fetch guide.
New model
DeepSeek-V4.1-Flash-1017 Update
DeepSeek V4.1 Flash has been upgraded to DeepSeek-V4.1-Flash-1017. The official web and APP models have also been updated to the new version. The API calling method and pricing remain unchanged — simply use deepseek-flash to access the latest model. Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks:
New model
DeepSeek-V4.1-Flash Release
Today, we officially release the DeepSeek-V4.1-Flash model. It is the smallest model in our new architecture family, with native multimodal visual understanding. The new architecture is designed for a higher capability ceiling, faster inference, higher throughput, and scaling to larger models. * Tested only on the pure-text subset of the HLE benchmark set.
New model
DeepSeek-V4-Flash-Vision-Exp Release
Today, the new multimodal vision understanding model DeepSeek-V4-Flash-Vision-Exp is now available on the DeepSeek API platform. This is an experimental model that can be accessed by setting model='deepseek-v4-flash-vision-exp'. * For the Code Agent text tasks in the public benchmark sets, the DeepSeek family models were tested using the DeepSeek Harness minimal mode as the framework, with the max effort level, topp=0.95, and temperature=1.0; in the ApexBench and Agents' Last Exam evaluations, the text model DeepSeek-V4-Flash ignores the multimodal elements within them.
New model
DeepSeek-V4-Pro Update
The GA release of DeepSeek-V4-Pro has been rolled out on the APP, Web, and API. The API calling method remains unchanged — simply set the model name to deepseek-v4-pro to use the latest version. The GA version of DeepSeek V4 Pro greatly enhances agent capabilities, with particularly significant performance improvements in production environments.
New model
DeepSeek-V4-Flash Update
The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to deepseek-v4-flash to use the latest version. Note 1: For the Code Agent tasks in the public benchmark sets, the official DeepSeek-V4-Flash was tested using the DeepSeek Harness minimal mode (to be released soon) as the framework, with the max effort level, topp=0.95, and temperature=1.0 Note 2: DSBench-FullStack is an internal full-stack development test set, and DSBench-Hard is an internal Coding Agent hard-problem test set
New model
DeepSeek-V4
The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set to deepseek-v4-pro or deepseek-v4-flash. The two legacy API model names, deepseek-chat and deepseek-reasoner, will be discontinued in three months (2026-07-24). During the current period, these two model names point to the non-thinking mode and thinking mode of deepseek-v4-flash, respectively.
New model
DeepSeek-V3.2
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2.
New model
DeepSeek-V3.2-Speciale
DeepSeek-V3.2-Speciale is served via a temporary endpoint: base_url=" https://api.deepseek.com/v3.2_speciale_expires_on_20251215 ". Same pricing as V3.2, no tool calls, available until Dec 15th, 2025, 15:59 (UTC Time).
New model
DeepSeek-V3.2-Exp
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2-Exp.
New model
DeepSeek-V3.1-Terminus
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1-Terminus. deepseek-chat corresponds to DeepSeek-V3.1-Terminus's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode. This update maintains the model's original capabilities while addressing issues reported by users, including:
New model
DeepSeek-V3.1
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1. deepseek-chat corresponds to DeepSeek-V3.1's non-thinking mode, while deepseek-reasoner corresponds to its thinking mode.
New model
deepseek-reasoner
deepseek-reasoner Model Upgraded to DeepSeek-R1-0528:
New model
deepseek-chat
deepseek-chat Model Upgraded to DeepSeek-V3-0324: Enhanced Reasoning Capabilities
New model
deepseek-reasoner
deepseek-reasoner is our new model DeepSeek-R1. You can invoke DeepSeek-V3 by specifying model='deepseek-reasoner'.. For details, please refer to: DeepSeek-R1 Release. For guides, please refer to: Thinking Mode
New model
deepseek-chat
The deepseek-chat model has been upgraded to DeepSeek-V3. The API remains unchanged. You can invoke DeepSeek-V3 by specifying model='deepseek-chat'.. For details, please refer to: introducing DeepSeek-V3
New model
deepseek-chat
The deepseek-chat model has been upgraded to DeepSeek-V2.5-1210, with improvements across various capabilities. Relevant benchmarking results include: Additionally, the new version of the model has optimized the user experience for file upload and webpage summarization functionalities.
New model
deepseek-coder & deepseek-chat Upgraded to DeepSeek V2.5 Model
The DeepSeek V2 Chat and DeepSeek Coder V2 models have been merged and upgraded into the new model, DeepSeek V2.5. For backward compatibility, API users can access the new model through either deepseek-coder or deepseek-chat.
DeepSeek API
API Launches Context Caching on Disk Technology
The DeepSeek API has innovatively adopted hard disk caching, reducing prices by another order of magnitude.
DeepSeek API
New API Features
Update API /chat/completions JSON Mode. Function Calling. Chat Prefix Completion（Beta）
New model
deepseek-coder
The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0724.
New model
deepseek-chat
The deepseek-chat model has been upgraded to DeepSeek-V2-0628. Model's reasoning capabilities have improved, as shown in relevant benchmarks:
New model
deepseek-coder
The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0614, significantly enhancing its coding capabilities. It has reached the level of GPT-4-Turbo-0409 in code generation, code understanding, code debugging, and code completion. Additionally, it possesses excellent mathematical and reasoning abilities, and its general capabilities are on par with DeepSeek-V2-0517.
New model
deepseek-chat
The deepseek-chat model has been upgraded to DeepSeek-V2-0517. The model has seen a significant improvement in following instructions, with the IFEval Benchmark Prompt-Level accuracy jumping from 63.9% to 77.6%. Additionally, on API end, we have optimized model ability to follow instruction filled in the system" part. This optimization has significantly elevated the user experience across a variety of tasks, including immersive translation, Retrieval-Augmented Generation (RAG), and more. The model's accuracy in outputting JSON format has been enhanced. In our internal test set, the JSON parsing rate increased from 78% to 85%. By introducing appropriate regular expressions, the JSON parsing rate was further improved to 97%.