Grok 4.6 Grok 4.6, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. See the Grok 4.6 overview and the announcement . August 11
Grok 4.5 Grok 4.5, SpaceXSI's model for coding, agentic tasks, and knowledge work, is now available on the xAI API. Priced at $2 / 1M input tokens and $6 / 1M output tokens, with configurable reasoning effort (low, medium, or high; default high). See the Grok 4.5 overview and the announcement .
deepseek-chat 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.
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. 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 upd
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
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.
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. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
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.
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 . 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
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. 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 upd
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.
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. 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 upd
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.
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. 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 upd
Grok 4.7 Grok 4.7, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API as grok-4.7 . It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. On the Responses API, grok-4.7 always returns reasoning.encrypted_content , even when include does not list it. It is also served on the US regional endpoint . Grok 4.7 Fast is the same model and costs 2x the standard token rates, or 1.5x for long-context requests. It's available only in Cursor and Grok Build, not on the public xAI API, and is billed through your plan there. See the Grok 4.7 overview and the announcement . September 17
Releasing the full suite of application APIs In the DeepSeek App (including the web version), web search, file input, URL reading, voice interaction and safety work together with model inference to form the conversation experience users know. Today we open these capabilities to developers: enable the corresponding parameters in the existing APIs to get conversation features such as web search, file input and URL reading, with the tool calls and context assembly handled by the service. The deepseek-flash model supports the following in the Messages, Responses and Chat Completions APIs: Web search : with thinking disabled and the deepseek_web_search tool enabled, the model runs web or image searches as the question requires and answers with citations. Deep thinking search : with thinking enabled and the deepseek_web_search tool enabled, the model searches the web and reads links on its own over multiple reasoning steps. File input : upload PDFs, Office files, images, and more; after plain-text extraction or rich-layout parsing, they are added to the conversation context for the model to answer from. URL reading : with the deepseek_read_url tool enabled, the model detects links in t
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.
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. 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 upd
Grok 4.6 Grok 4.6, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. See the Grok 4.6 overview and the announcement . August 11
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.
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. 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 upd
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.
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. 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 upd
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.
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. 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 upd
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.
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. 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 upd
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.
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. 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 upd
Grok 4.7 Grok 4.7, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API as grok-4.7 . It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. On the Responses API, grok-4.7 always returns reasoning.encrypted_content , even when include does not list it. It is also served on the US regional endpoint . Grok 4.7 Fast is the same model and costs 2x the standard token rates, or 1.5x for long-context requests. It's available only in Cursor and Grok Build, not on the public xAI API, and is billed through your plan there. See the Grok 4.7 overview and the announcement . September 17
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.
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. 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 upd
Grok 4.6 Grok 4.6, SpaceXSI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API. It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. See the Grok 4.6 overview and the announcement . August 11
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.
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. Performance–cost Pareto improvement Compared with the previous DeepSeek V4.1, the new model delivers substantial improvements across benchmarks: HLE (w/o tools): 42.6 (44.0*) Terminal-Bench 4.0: 42.3 DeepSWE v1.1: 77.0 ProgramBench: 29.1 NL2Repo-Bench: 68.2 Automation-Bench v1.0.6: 60.5 Agents' Last Exam: 35.4 Apex Bench v1.1: 72.1 Chartography (w/tools): 83.0 BabyVision (w/tools): 92.5 ZeroBench-main (w/tools): 51.0 * Tested only on the pure-text subset of the HLE benchmark set. Terminal-Bench 4.0 was tested with the Claude Code framework, and DeepSWE with the Mini-SWE-V2 framework. ZeroBench-main was evaluated with Pass@5. While improving performance, we also reduced the model's task runtime and output length, enabling users to complete tasks at lower cost and higher speed and achieving a new performance–cost Pareto optimum across multiple harnesses. We specifically optimized for DeepSeek Harness, Ten
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.
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. 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 upd
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.
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. 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 upd
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
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.
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: 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.
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. 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 upd
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.
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. 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 upd
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.