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-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.
Hey all, I own a couple of consultancies where we set up companies and do general business advisory. Earlier this year, I started working on our websites myself and ended up coding a free tool that checks company name availability and legality. It's getting a lot of traffic (by my standards—around 40–50 people per country), and now I'm trying to figure out how to monetize it. Do you have any suggestions?
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.
Grok Build Grok Build is now available in beta. Use the interactive TUI, run headlessly in scripts, or build apps and orchestrators with the Agent Client Protocol. Install with a single command: Bash curl -fsSL https://x.ai/cli/install.sh | bash For more details, see the Grok Build docs . May 1
I built Klistra: describe your video idea and add your logo, photos or other assets, Klistra designs and animates a video for you, exported for every screen size, with fonts, media and logos kept exact. Deterministic renders make features exact and isolated, allowing for superior control and iteration compared to diffusion models. Here's a short demo render where I made an ad for Klistra itself: https://app.klistra.ai/s/4EQoWCe37SkYz5nThgegzw As a solo dev with a lot of projects going on, I found myself needing to make short promos or explainer videos. Not being familiar with animation software, I had the idea to use Claude to code up those videos and export them as video files. In the process of creating these clips I stumbled into a bunch of bugs and setup needed to make it work reliably. The list of features I wanted for better control and feedback kept growing and I needed to sign up for a bunch of services to get music, voiceovers and other media into my project. I couldn't find an existing service that had everything I wanted. Seeing these hurdles and that the technology was only easily accessible to people already confident with coding agents, I started working on Klistra, a
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.
Grok Build Grok Build is now available in beta. Use the interactive TUI, run headlessly in scripts, or build apps and orchestrators with the Agent Client Protocol. Install with a single command: Bash curl -fsSL https://x.ai/cli/install.sh | bash For more details, see the Grok Build docs . May 1
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-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.
What if every Erlang process were an operating-system process? With as much system code and drivers written in Erlang itself. This is something I was pondering for a while, and finally was able to prototype thanks to AI coding agents. erXos is a capability-based microkernel OS in Erlang: drivers, filesystems, and the network stack are all supervised Erlang processes, same as any app. The kernel itself is Fiasco, in C++, slightly modified for erXos needs. This is an OS I wanted for a long time: an Erlang machine where every BEAM process is a process visible to the OS and scheduler, not something bolted on top. You can try it right now with nothing to install: there is an emulator on the website that boots the whole OS in the browser ARM64 emulator. At the rc prompt, try `ps`, `top`, `ping` or `erl` and write any kind of erlang code. There's a Pi 4 SD image and a QEMU image too. The goal is to build an ultra-reliable microkernel OS with hot code loading and both system and BEAM-based isolation. The latter is one thing that would allow you to run millions of processes on the system, something that would be prohibitive on a microkernel alone due to the context switch overhead. Capabili
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.
Grok Build Grok Build is now available in beta. Use the interactive TUI, run headlessly in scripts, or build apps and orchestrators with the Agent Client Protocol. Install with a single command: Bash curl -fsSL https://x.ai/cli/install.sh | bash For more details, see the Grok Build docs . May 1