101 articles in "API/SDK" — sorted by importance and recency
Claude.ai Unavailable and Increased Errors on the API
On April 28, 2026, Anthropic identified issues preventing access to Claude.ai and resulting in increased errors on the API, including login paths for Claude Code. They are working to resolve these iss
Runway Introduces Aleph: A New AI Model
Runway has introduced a new AI model called 'Runway Aleph'. Aleph is a powerful tool for generating text, images, and video editing. Users can easily create various media through an intuitive interfac
新しいFLUX1.1 [pro]は、生成速度が6倍速くなり、画像の品質と多様性が向上しました。一方、FLUX.1 Kontextはテキストと画像を組み合わせた生成を行い、最大8倍の速度で編集が可能です。どちらも先進的な機能を持ちますが、用途に応じた特性が異なります。
Anthropicの新リリースFLUX.1ツールは、特にインペインティング機能を強化し、FLUXのエコシステムを向上させます。一方、過去のFLUXモデルはAzureでの利用が注目されています。新機能の追加と古いモデルの廃止がどのように影響するかを比較しました。
FLUX1.1 [pro]の新バージョンが生成速度を6倍に向上させ、BFL APIが一般提供されることで、開発者は新しい画像生成技術を利用しやすくなります。過去バージョンとの比較を通じて、進化した機能や性能を紹介します。
Announcing the FLUX Pro Finetuning API
Black Forest Labs has announced the FLUX Pro Finetuning API, enabling creators to customize the FLUX Pro model with their own images and concepts. This API improves generative models that lack underst
Release of FLUX.1 Tools for Enhanced Image Control
Anthropic has announced FLUX.1 Tools, a suite designed to enhance control and steerability for its base text-to-image model FLUX.1. FLUX.1 Fill introduces advanced inpainting capabilities that outperf
Announcing FLUX1.1 [pro] and the BFL API
FLUX1.1 [pro] has been released with a 6x faster generation speed compared to its predecessor. The BFL API is now generally available, allowing developers and businesses to integrate cutting-edge imag
Introducing SAM Audio: The First Unified Multimodal Model for Audio Separation
Meta AI has announced a new audio processing technology called SAM Audio. This technology allows users to easily isolate any sound from complex audio mixtures using natural multimodal prompts, simplif
Announcing the FLUX Pro Finetuning API
Black Forest Labs announced the FLUX Pro Finetuning API, allowing creators to customize the FLUX Pro model with their own images and concepts. This feature enhances control over generated content, add
Announcing FLUX1.1 [pro] and the BFL API
Today, FLUX1.1 [pro] has been released, featuring six times faster generation than its predecessor FLUX.1 [pro], with improvements in image quality and diversity. The beta BFL API is also now availabl
Introducing the Uni-1.1 API: Intelligence You Can Direct
Luma Labs has announced the Uni-1.1 API, a REST interface for image generation and natural language editing. This API enables developers to transform creative workflows and enhance creativity. Uni-1 p
Mistral AIの新モデル「Mistral Large」と過去のリリースを比較します。Mistral Largeは32Kトークンに対応し、高い推論能力を持つ一方、過去のインターフェースやカスタマイズ機能は異なる方向性を示しています。これにより、ユーザーはより幅広い選択肢を得ることができます。
Mistral AIが発表した新しいコードモデル「Codestral」と、過去の言語モデル「Mistral Large」を比較します。両者は異なる用途に特化しており、特にCodestralは多様なプログラミング言語に対応。コンテキストウィンドウのサイズは共通ですが、機能やターゲットユーザーに違いがあります。
Mistral AIの新しいコード生成モデル「Codestral Mamba」と、以前発表された言語モデル「Mistral Large」を比較します。両者は異なる用途に特化しており、性能や機能においても大きな違いがあります。特に、Codestral Mambaは無限長のシーケンス処理能力を持ち、開発者にとって新たな可能性を提供しています。
新しいCodestral 25.01は、初代Codestralに比べて約2倍速くコードを生成できるよう改善されました。80以上のプログラミング言語をサポートし、企業向けのローカルデプロイ機能も搭載されています。生産性が大幅に向上するポイントが魅力です。
Introducing Voice Changer: A New Tool for Voice Conversion
ElevenLabs has announced a new voice conversion tool called 'Voice Changer.' This tool allows users to convert a recording of one voice to sound as if spoken by another, preserving the original emotio
Exploring the Potential of AI for Multilingual Speech Generation
Advancements in AI and machine learning enable the generation of natural-sounding speech in various languages. This technology helps in the international dissemination of content, allowing individuals
Introduction of Voice Design - The First Generative AI for Audio
ElevenLabs has introduced a new voice generation model called 'Voice Design.' This technology allows users to create new voices from scratch by selecting core attributes such as gender, age, and accen
Revolutionizing Content Creation with Voice Conversion Technology
Voice conversion allows transforming one person's voice into another while preserving the original intonation and emotional delivery. ElevenLabs is developing an automatic dubbing tool that utilizes t
Stability AI Expands Image Services to Amazon Bedrock
Stability AI enhances its partnership with Amazon Web Services, launching professional-grade image editing capabilities on Amazon Bedrock. The new Image Services, available as API solutions, support c
Mistral AI Announces New Model 'Mistral Large'
Mistral AI has announced its latest language model, 'Mistral Large', which features top-tier reasoning capabilities and is available through Azure. This model supports complex multilingual tasks and a
Mistral AI Launches New AI Endpoints in Early Access
Mistral AI is offering new AI endpoints in early access. There are three chat endpoints and one embedding endpoint, each with different performance and price trade-offs. Notably, Mistral-tiny is cost-
Introducing Customization Features from Mistral AI
Mistral AI has introduced new model customization features, allowing users to easily tailor Mistral's AI models to their specific needs, reducing costs and required expertise. With the new API and SDK
Mistral AI Unveils Its First Code Model, Codestral
Mistral AI has announced Codestral, its first AI model designed for code generation. This model supports over 80 programming languages and assists developers in writing code. Codestral saves time and
Introducing Codestral Mamba: A New Code Generation Model
Mistral AI has announced a new code generation model called Codestral Mamba, specialized for coding tasks. This model is available for free use, modification, and distribution, aiming to enhance code
New Codestral 25.01 Released, Enhancing Coding Productivity
Mistral AI has announced the new Codestral 25.01 model. It generates and completes code about twice as fast as its predecessor. Supporting over 80 programming languages, it significantly boosts produc
New Advancements in Developing Generative AI Applications
Mistral AI announced new features to simplify the development of generative AI applications. Developers can customize models like Mistral Large 2 and Codestral to integrate AI capabilities tailored to
Mistral introduces cost-effective batch API for AI developers
Mistral has announced a cost-effective batch API for AI developers, allowing for 50% lower costs compared to traditional synchronous API calls. It efficiently processes high-volume requests, enabling
Use Codex Anywhere with the ChatGPT Mobile App
With the ChatGPT mobile app, you can now use Codex anywhere. This allows you to monitor, steer, and approve coding tasks in real time across various devices and remote environments.
Major Upgrade to DeepSeek API with New Features
The DeepSeek API has received a major upgrade, now supporting chat prefix completion, function calling, and JSON output. This allows the model to return output in valid JSON format, facilitating data
DeepSeek API Introduces Disk-Based Context Caching
The DeepSeek API introduces disk-based context caching, allowing for the detection of duplicate user inputs to reduce service latency and cut costs by up to 90%. Users can expect quicker responses eve
DeepSeek-V2.5 Released: A Fusion of General and Coding Capabilities
DeepSeek-V2.5 has been officially launched, combining general conversational and coding capabilities. The new model aligns better with user preferences and shows improvements in writing and instructio
DeepSeek V2.5 Officially Released, Anticipation for Next-Gen Models
DeepSeek V2.5 has been released, introducing an Internet search feature for real-time answers. This version improves performance across benchmarks like math, coding, writing, and roleplay, marking the
Introducing DeepSeek-V3: The Biggest Leap Forward Yet
DeepSeek has announced the new version, DeepSeek-V3, marking the biggest leap forward yet. Significant improvements in AI-related technologies and features are anticipated. Refer to the official docum
Advancing voice intelligence with new models in the API
New real-time voice models have been added to the OpenAI API. These models can reason, translate, and transcribe speech, enabling more natural and intelligent voice interactions, allowing users to int
Higher usage limits for Claude and a compute deal with SpaceX
Anthropic has announced raised usage limits for Claude and a new compute partnership with SpaceX, gaining over 300 megawatts of new capacity. This benefits Claude Pro and Claude Max users directly. Ke
Release of GPT-5.5 Instant System Card
OpenAI has announced the GPT-5.5 Instant System Card, a concise summary of the features and characteristics of the GPT-5.5 model. It is designed to help users quickly understand the attributes of the
KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
KAME is a new tandem architecture designed for real-time speech-to-speech conversational AI. This architecture aims to enhance knowledge during conversations. AI that converts speech to speech must pr
Learning to Orchestrate Agents in Natural Language with the Conductor
Anthropic has introduced a new tool called 'Conductor' that enables orchestration of multiple AI agents using natural language. Developers can utilize this to efficiently coordinate AI interactions, a
DeepSeek V4 Preview Release Now Live and Open-Sourced
The DeepSeek V4 preview is officially live, introducing cost-effective 1M context length. It features DeepSeek-V4-Pro, rivaling top closed-source models, and DeepSeek-V4-Flash as a fast, economical op
Sakana Fugu: A Multi-Agent Orchestration System as a Foundation Model
Sakana Fugu is designed as a multi-agent orchestration system, functioning as part of an AI foundation model. This system enables multiple AI agents to collaborate effectively on tasks, allowing users
Release of DeepSeek-V3.2 and V3.2-Speciale Models
DeepSeek has launched two new models: DeepSeek-V3.2 and V3.2-Speciale. V3.2 is available on app, web, and API, offering GPT-5 level performance. V3.2-Speciale maximizes reasoning capabilities and is A
Introducing DeepSeek-V3.2-Exp: New Features and Price Cut
DeepSeek has launched its new experimental model, V3.2-Exp, built on V3.1-Terminus. It introduces DeepSeek Sparse Attention (DSA) for faster and more efficient training and inference on long contexts.
DeepSeek-V3.1 Release - The First Step Toward the Agent Era
DeepSeek-V3.1 has been released, marking the first step toward the agent era. This version features hybrid inference (two modes: Think and Non-Think), faster answers, and enhanced tool usage. It suppo
Announcing DeepSeek-V3-0324 Release
The latest release, DeepSeek-V3-0324, features a significant boost in reasoning performance, enhancing AI capabilities and making the tool more user-friendly.
DeepSeek-R1 Release and API Documentation Launch
DeepSeek has released the fully open-source DeepSeek-R1 model, matching OpenAI-o1 performance. Released under the MIT license, users can commercialize freely. The API is live, enabling fine-tuning for
Official Launch of DeepSeek App
DeepSeek has launched a new app available on App Store and Google Play for free, without ads or in-app purchases. Users can log in easily using email, Google Account, or Apple ID, and chat history syn
Release Notes for Claude Code v2.1.143
In Claude Code v2.1.143, new features include plugin dependency enforcement, background session model retention, and default enabling of the PowerShell tool. Various bug fixes have also been implement
Announcing the Mistral AI Fine-tuning Hackathon
Mistral AI announced a fine-tuning hackathon taking place from June 5 to 30, 2024. Participants can experiment with the new fine-tuning API and showcase their projects. The top three projects will rec
Release of anthropic-sdk-python version 0.102.0
The Anthropic Python SDK has been updated to version 0.102.0. This update includes new features such as the addition of BetaManagedAgentsSearchResultBlock types and beta support for cache diagnostics.
How NVIDIA engineers and researchers build with Codex
NVIDIA engineers and researchers use Codex in conjunction with GPT-5.5 to turn research ideas into runnable experiments and ship production systems. This process aims to efficiently develop and implem
Release of Claude Code v2.1.139
The release of Claude Code version 2.1.139 introduces various new features and bug fixes. Enhancements include an agent view and new commands that improve usability. Notably, the new `/goal` command a
Release of anthropics/anthropic-sdk-typescript v0.3.0
Anthropic has released a new version v0.3.0 of the TypeScript SDK. This update adds an AWS (Amazon Web Services) client for the Claude platform, enabling developers to more easily utilize Claude in AW
Claude Code v2.1.133 Release Notes
The new version v2.1.133 of Claude Code has been released. This update introduces a setting to choose the base reference for worktrees and allows specifying custom binaries for Linux/WSL. Improvements
Release of Anthropic SDK v0.95.0
Anthropic SDK version v0.95.0 has been released, adding support for Managed Agents multiagents, outcomes, webhooks, and vault validation. Additionally, a bug related to webhook configuration has been
Release of anthropic-sdk-python v0.100.0
Anthropic announced the release of version 0.100.0 of its Python SDK. This update introduces support for Managed Agents multiagents and outcomes, webhooks, and vault validation. Additionally, webhook
Release of anthropic-sdk-typescript v0.94.0
Anthropic has released a new version v0.94.0 of its TypeScript SDK. This version enhances the token exchange feature by allowing workspace targeting for OIDC (OpenID Connect) federation, providing dev
Reduce friction and latency for long-running jobs with Webhooks in Gemini API
Google's Gemini API introduces Webhooks to reduce friction and latency for long-running jobs. Webhooks provide an event-driven approach, allowing notifications when processing is complete, enabling mo
Resolved Issues with Structured Outputs on the API
Between April 22, 16:10 and April 23, 01:59, an issue arose affecting the quality of model responses using structured outputs via the Anthropic API. Outputs with grammar requirements were specifically
Key Changes in Claude Code v2.1.118
The latest version v2.1.118 of Claude Code introduces vim visual modes and improves usage statistics access. It simplifies custom theme creation and plugin release management while fixing OAuth authen
String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation
This article discusses prompting techniques for language models (LLMs) to achieve distribution-faithful and diverse generation. It focuses on how to enhance the diversity of generated content and how
New Features and Improvements in Claude Code v2.1.111
The new version v2.1.111 of Claude Code has been released with multiple new features and enhancements. A new 'xhigh' effort level allows users to balance speed and intelligence. Auto mode is now avail
Anthropic SDK Python version 0.96.0 Released
The new version 0.96.0 of Anthropic SDK Python has been released. This update includes the addition of claude-opus-4-7, token budgets, and user profile features. The release doctor workflow has also b
Release of Anthropics SDK v0.90.0
The Anthropics SDK version 0.90.0 has been released, featuring the addition of claude-opus-4-7, token budgets, and user profiles. The release doctor workflow has also been removed, allowing developers
Release of anthropic-sdk-python v0.95.0
The new version v0.95.0 of the Anthropic SDK has been released. In this version, Sonnet and Opus 4 are marked as deprecated, and the Mantle client now uses an authentication header. These changes are
New ways to balance cost and reliability in the Gemini API
Google introduces new features in the Gemini API to balance cost and reliability. The addition of Flex and Priority Inference allows developers to make flexible choices according to various needs, ena
Release of DeepSeek-V3.1-Terminus
The latest update, DeepSeek-V3.1-Terminus, has been released. It builds on the strengths of the previous version, V3.1, while addressing user feedback. Improvements include enhanced language consisten
DeepSeek-R1-0528 Release Announcement
DeepSeek has released version R1-0528, which improves benchmark performance and enhances front-end capabilities. It reduces AI hallucinations and supports JSON output and function calling. There are n
How Data Science Teams Utilize Codex for Various Tasks
This article showcases how data science teams can leverage Codex to generate root-cause analyses, impact readouts, KPI memos, scoped analyses, and dashboard specifications from real work inputs, enhan
Changes in Claude Code v2.1.142
The new version v2.1.142 of Claude Code has been released, featuring various improvements and bug fixes. Notable changes include new flags for configuration, a default switch to Opus 4.7, and enhancem
Changes in Claude Code v2.1.141
The latest update of Claude Code, v2.1.141, introduces new features such as terminal notifications and window title additions, HTTPS cloning for GitHub plugins, and an environment variable for workspa
Release of anthropic-sdk-typescript v0.96.0
The new version v0.96.0 of the Anthropic SDK has been released, featuring the addition of BetaManagedAgentsSearchResultBlock types and support for cache diagnostics beta. A bug fix for the zod library
Release of Anthropic SDK v0.101.0
The new version v0.101.0 of the Anthropic SDK has been released. A new feature includes the addition of an AWS client for the Claude platform, and bug fixes have been implemented. Specifically, a miss
Release of anthropic-sdk-typescript version 0.95.2
A new version 0.95.2 of the TypeScript SDK from Anthropic has been released. This update includes bug fixes and functional improvements. More details can be found in the GitHub release notes.
Release of Claude Code v2.1.138
The release of Claude Code version 2.1.138 includes internal fixes aimed at improving system stability and performance. Refer to the official release notes for more details.
Claude Code v2.1.137 Release Notes
The new version v2.1.137 of Claude Code has been released. This update fixes an issue where the VSCode extension failed to activate on Windows, allowing users to utilize their development environment
Claude Code v2.1.136 Release Notes
The new version v2.1.136 of Claude Code has been released. This update includes re-enabling the session quality survey for enterprises, adding auto mode classifier rules that block unconditionally reg
Release of anthropic-sdk-typescript v0.95.1
A new version v0.95.1 of the TypeScript SDK by Anthropic has been released. This version includes the redaction of API key headers in debug logs, enhancing user security. The full update details can b
Release Notes for Claude Code v2.1.131
The latest version v2.1.131 of Claude Code has been released. This update fixes an issue where the VS Code extension failed to activate on Windows due to a hardcoded build path. It also resolves a pro
Updates in Claude Code v2.1.129
The new version v2.1.129 of Claude Code has been released, adding features like fetching plugins from URLs and an environment variable for forced synchronized output. Various bug fixes and improvement
Release of Anthropic SDK version 0.99.0
The latest version 0.99.0 of the Anthropic SDK has been released. This update adds a feature to allow targeting a workspace for OIDC (OpenID Connect) federation token exchange. Detailed changelog is a
Updates in Claude Code v2.1.128
The new version v2.1.128 of Claude Code has been released with various feature improvements and bug fixes. Notably, server connection status display and plugin handling have been enhanced, improving u
Release of anthropic-sdk-python version 0.98.1
Version 0.98.1 of Anthropic's SDK 'anthropic-sdk-python' has been released. This version includes a fix for a typo in the examples. You can check the full change log on the GitHub release page.
Release of anthropic-sdk-python version 0.98.0
Anthropic has released version 0.98.0 of its Python SDK. This update includes improvements to Managed Agents APIs, the addition of Workload Identity Federation, interactive OAuth, and auth profiles. B
Release Information for Anthropic SDK Version 0.93.0
A new version 0.93.0 of the Anthropic SDK has been released. This version introduces Workload Identity Federation, interactive OAuth, and auth profiles, allowing developers to utilize more convenient
New Features and Fixes in Claude Code v2.1.126
The new release v2.1.126 of Claude Code includes several new features and bug fixes. The model selection has been improved, and a command to purge project state has been added. Enhancements have been
Release of anthropic-sdk-typescript version 0.29.1
The new version 0.29.1 of the Anthropic SDK TypeScript has been released. This update includes a fix that throws APIError for error events delivered in chunk frames. Details are available in the GitHu
Anthropic SDK v0.92.0 Released
Anthropic SDK version 0.92.0 has been released. Key improvements include enhancements to Managed Agents APIs and support for setting headers via environment variables. A bug fix was made to throw APIE
Update information for Claude Code v2.1.123
The latest version of Claude Code, v2.1.123, has been released. This update fixes an issue with OAuth authentication where a 401 error would occur when a specific environment variable was set. This al
Overview of Changes in Claude Code v2.1.122
The new version v2.1.122 of Claude Code has been released, featuring the addition of environment variables and improvements to session search using PR URLs, alongside various bug fixes. Key enhancemen
Claude Code v2.1.121 Release Notes
The new version v2.1.121 of Claude Code introduces the `alwaysLoad` option for MCP server config, allowing all tools to be immediately available. New commands for cleaning up plugin dependencies and i
Release of Anthropic SDK v0.91.1
Anthropic has released a new version of its SDK, v0.91.1. This update includes a bug fix for memory files, which now use a restrictive file mode, and has separated the running of the code formatter Pr
Updates in Claude Code v2.1.119 Release
The new version v2.1.119 of Claude Code has been released, adding features like persistent settings, customizable PR links, and various execution improvements. Notably, support for GitLab and Bitbucke
Release of Anthropic SDK version 0.97.0
A new version 0.97.0 of the Anthropic SDK has been released. This version includes the public beta of CMA Memory, fixes for API specification errors, and restoration of missing features. Performance i
Release of anthropic-sdk-typescript version 0.29.0
The latest version 0.29.0 of the Anthropic SDK for TypeScript was released on April 23, 2026. This version introduces a new feature that uses an authentication header for the mantle client. A detailed
Release Information for Anthropic SDK v0.91.0
The Anthropic SDK has released version v0.91.0, featuring several new functionalities and bug fixes. Key new features include the public beta of CMA Memory and the addition of an auth header for the m
Release Notes for Claude Code v2.1.117
The new version v2.1.117 of Claude Code has been released. New features include enabling forked subagents on external builds, loading mcpServers for main-thread agent sessions, persistent selections,
Release of Anthropic SDK v0.89.0
The new version v0.89.0 of the Anthropic SDK has been released. This update marks Sonnet and Opus 4 as deprecated and adds missing events to the streaming functionality. Manual updates have also been
Release of Anthropic SDK Python version 0.94.1
The new version 0.94.1 of the Anthropic SDK for Python has been released. This update adds missing events in the streaming functionality, allowing developers to utilize the SDK more smoothly. Detailed
Release Notes for Anthropic SDK v0.94.0
Anthropic SDK version 0.94.0 has been released. This update includes support for the EU region and improvements in file data transmission parameters. Additionally, examples in the documentation have b