Change Log

Date: 2026-07-31â

DeepSeek-V4-Flash Updateâ

The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged â simply set the model name to deepseek-v4-flash to use the latest version.

Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview:

  • Terminal Bench 2.1: 82.7
  • NL2Repo: 54.2
  • Cybergym: 76.7
  • DeepSWE: 54.4
  • Toolathlon verified: 70.3
  • Agent Last Exam: 25.2
  • Automation Bench (Public): 25.1
  • DSBench-FullStack: 68.7
  • DSBench-Hard: 59.6

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

The official V4-Flash natively supports the Responses API format and is specifically adapted for Codex. For the specific configuration, please refer to the documentation.

DeepSeek-V4-Flash-0731 keeps the same model architecture and size as DeepSeek-V4-Flash-preview, and was only re-post-trained.

Note: This update only upgrades the DeepSeek-V4-Flash API. The DeepSeek-V4-Pro API and the APP/WEB models are unchanged.

The official release of DeepSeek-V4-Pro will follow soon.

Date: 2026-04-24â

DeepSeek-V4â

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.

For more details, please refer to this documentation.

Date: 2025-12-01â

DeepSeek-V3.2â

Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2.

  • deepseek-chatcorresponds to DeepSeek-V3.2's- non-thinking mode
  • deepseek-reasonercorresponds to DeepSeek-V3.2's- thinking mode

DeepSeek-V3.2-Specialeâ

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).

For more details, please refer to this documentation.

Date: 2025-09-29â

DeepSeek-V3.2-Expâ

Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2-Exp.

  • deepseek-chatcorresponds to DeepSeek-V3.2-Exp's- non-thinking mode
  • deepseek-reasonercorresponds to DeepSeek-V3.2-Exp's- thinking mode

For more details, please refer to this documentation.

Date: 2025-09-22â

DeepSeek-V3.1-Terminusâ

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:

  • Language consistency: Reduced occurrences of Chinese-English mixing and occasional abnormal characters;
  • Agent capabilities: Further optimized the performance of the Code Agent and Search Agent.

Date: 2025-08-21â

DeepSeek-V3.1â

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.

  • Key updates in DeepSeek-V3.1:
  • Hybrid reasoning architecture: A single model supports both thinking mode and non-thinking mode
  • Improved reasoning efficiency: Compared to DeepSeek-R1-0528, DeepSeek-V3.1-Think provides answers in significantly less time
  • Enhanced agent capabilities: With post-training optimization, the new model achieves major improvements in tool usage and intelligent agent tasks- SWE-bench Verified: 66.0
  • SWE-bench Multilingual: 54.5
  • Terminal-bench: 31.3

Date: 2025-05-28â

deepseek-reasonerâ

deepseek-reasoner Model Upgraded to DeepSeek-R1-0528:

  • Enhanced Reasoning Capabilities- Significant benchmark improvements (Pass@1)
  • AIME 2025: 70.0 â 87.5 (+17.5)
  • GPQA: 71.5 â 81.0 (+9.5)
  • LCB_v6: 63.5 â 73.3 (+9.8)

  • Aider: 57.0 â 71.6 (+14.6)

  • Note: Complex reasoning tasks may consume more tokens compared to legacy R1 version.

  • Significant benchmark improvements (Pass@1)

  • Optimized Front-end Development- Generated web pages and games now feature improved aesthetics.

  • Reduced Hallucinations- Significantly suppressed hallucination issues present in legacy R1 version.

  • JSON Output & Function Calling Support- Function call performance:

  • Tau-bench score: 53.5 (Airline) / 63.9 (Retail)

  • Function call performance:

Date: 2025-03-24â

deepseek-chatâ

deepseek-chat Model Upgraded to DeepSeek-V3-0324:

  • Enhanced Reasoning Capabilities- Significant improvements in benchmark performance:
  • MMLU-Pro: 75.9 â 81.2 (+5.3)
  • GPQA: 59.1 â 68.4 (+9.3)
  • AIME: 39.6 â 59.4 (+19.8)
  • LiveCodeBench: 39.2 â 49.2 (+10.0)

- Significant improvements in benchmark performance:

Optimized Front-End Web Development- Improved accuracy in code generation
- More aesthetically pleasing web pages and game front-ends

  • Upgraded Chinese Writing Proficiency- Enhanced style and content quality:
  • Aligned with the R1 writing style
  • Better quality in medium-to-long-form writing

- Enhanced style and content quality:

Feature Enhancements- Improved multi-turn interactive rewriting
- Optimized translation quality and letter writing

  • Improved Chinese Search Capabilities- Enhanced report analysis requests with more detailed outputs

  • Function Calling Improvements- Increased accuracy in Function Calling, fixing issues from previous V3 versions

Date: 2025-01-20â

deepseek-reasonerâ

  • deepseek-reasoneris 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

Date: 2024-12-26â

deepseek-chatâ

  • The deepseek-chatmodel has been upgraded to DeepSeek-V3. The API remains unchanged. You can invoke DeepSeek-V3 by specifyingmodel='deepseek-chat'.
  • For details, please refer to: introducing DeepSeek-V3

Date: 2024-12-10â

deepseek-chatâ

The deepseek-chat model has been upgraded to DeepSeek-V2.5-1210, with improvements across various capabilities. Relevant benchmarking results include:

  • Mathematical: Performance on the MATH-500 benchmark has improved from 74.8% to 82.8% .
  • Coding: Accuracy on the LiveCodebench (08.01 - 12.01) benchmark has increased from 29.2% to 34.38% .
  • Writing and Reasoning: Corresponding improvements have been observed in internal test datasets.

Additionally, the new version of the model has optimized the user experience for file upload and webpage summarization functionalities.

Date: 2024-09-05â

deepseek-coder & deepseek-chat Upgraded to DeepSeek V2.5 Modelâ

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.

The new model significantly surpasses the previous versions in both general capabilities and code abilities.

The new model better aligns with human preferences and has been optimized in various areas such as writing tasks and instruction following:

  • ArenaHard win rate improved from 68.3% to 76.3%
  • AlpacaEval 2.0 LC win rate increased from 46.61% to 50.52%
  • MT-Bench score rose from 8.84 to 9.02
  • AlignBench score increased from 7.88 to 8.04

The new model has further enhanced its code generation capabilities based on the original Coder model, optimized for common programming application scenarios, and achieved the following results on the standard test set:

  • HumanEval: 89%
  • LiveCodeBench (January-September): 41%

Date: 2024-08-02â

API Launches Context Caching on Disk Technologyâ

The DeepSeek API has innovatively adopted hard disk caching, reducing prices by another order of magnitude.

For more details on the update, please refer to the documentation Context Caching is Available 2024/08/02.

Date: 2024-07-25â

New API Featuresâ

  • Update API /chat/completions- JSON Mode
  • Function Calling
  • Chat Prefix Completionï¼Betaï¼

  • 8K max_tokensï¼Betaï¼

  • New API /completions- FIM Completionï¼Betaï¼

For more details, please check the documentation New API Features 2024/07/25

Date: 2024-07-24â

deepseek-coderâ

The deepseek-coder model has been upgraded to DeepSeek-Coder-V2-0724.

Date: 2024-06-28â

deepseek-chatâ

The deepseek-chat model has been upgraded to DeepSeek-V2-0628.

Model's reasoning capabilities have improved, as shown in relevant benchmarks:

  • Coding: HumanEval Pass@1 79.88% -> 84.76%
  • Mathematics: MATH ACC@1 55.02% -> 71.02%
  • Reasoning: BBH 78.56% -> 83.40%

In the Arena-Hard evaluation, the win rate against GPT-4-0314 increased from 41.6% to 68.3%.

The model's role-playing capabilities have significantly enhanced, allowing it to act as different characters as requested during conversations.

Date: 2024-06-14â

deepseek-coderâ

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.

Date: 2024-05-17â

deepseek-chatâ

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%.