Newest Releases

Windsurf (Codeium)

✓

AI coding IDE with Cascade agent, Tab completions, and prompt credits

Codeium now directs to Windsurf, an AI coding IDE and plugin suite featuring the Cascade agent, Tab completions, and prompt credits usable across providers (OpenAI, Claude, Gemini, xAI). Free users get 25 prompt credits per month with unlimited Tab completions/inline edits; paid tiers add Fast Context, Windsurf Reviews, admin controls, and more credits. Windsurf also ships the in-house SWE-1.5 coding model alongside access to external models (see pricing for details).

Amp (formerly Cody)

✓

Agentic coding by Sourcegraph with CLI and VS Code extension

Amp (formerly Cody) is Sourcegraph’s agentic coding tool. It runs as a VS Code extension or CLI, uses frontier models, and focuses on autonomous reasoning, multi-step edits, and shareable threads. Built for teams, it offers enterprise security/compliance options and uses Sourcegraph context to reason across codebases. Public pricing is not listed; teams start with free credits and then talk to sales.

Continue

✓

Open-source, model-agnostic AI coding assistant for VS Code and JetBrains

Continue is an open-source coding assistant that lets developers use their own models (OpenAI, Anthropic, local via Ollama/LM Studio) with custom prompts and workflows. It runs as a VS Code and JetBrains extension, supports chat and completions, and can be self-hosted or run fully local for privacy.

LangChain

✓

Open-source framework for LLM apps with LangSmith observability

LangChain is an open-source framework for building LLM apps with composable chains, agents, tools, and RAG. It supports Python and TypeScript, integrates with major model providers and vector stores, and pairs with LangSmith for tracing, monitoring, and evals.

LangGraph

✓

Graph-based framework for controllable, stateful AI agents

LangGraph is an open-source framework in the LangChain ecosystem for building stateful, multi-step agents with controllable graphs (single, multi-agent, hierarchical flows). It supports human-in-the-loop interrupts, streaming, memory, and tool use, and can be deployed via LangGraph Platform or self-hosted OSS.

OpenAI API

✓

API access to GPT-5.1, GPT-5, GPT-4o, images, audio, and tools

OpenAI’s API gives developers pay-per-use access to the latest GPT models (GPT-5.1, GPT-5, GPT-4o, GPT-4.1, GPT-4.1 mini/nano, o-series), plus images (GPT-Image-1), speech (gpt-audio, Whisper), embeddings, and moderation. It supports tool calling, structured outputs, Assistants/Responses/Chat Completions, Batch, Realtime, prompt caching, fine-tuning, and file/image/audio endpoints. Pricing is metered per model; for example, GPT-5.1 Standard is $1.25 per 1M input ($0.125 cached) and $10 per 1M output, or $0.625 / $5 via Batch (see pricing page for all models).

OpenAI Codex (deprecated)

✓

Legacy code models retired on March 23, 2023

OpenAI Codex was the early natural-language-to-code model family (e.g., code-davinci-002, code-cushman-002). Per OpenAI’s deprecation notice, all Codex models were shut down on March 23, 2023, with GPT-4o and newer GPT models recommended for coding tasks. The Codex API is no longer available.

Qodo

✓

AI test generation and PR review (formerly CodiumAI)

Qodo (rebranded from CodiumAI) provides AI-assisted test generation and PR/code review for IDEs and git workflows. It offers Qodo Gen for test suggestions in-editor and Qodo Merge for automated PR feedback to improve coverage and quality.

GPT-4o

✓

OpenAI flagship GPT with text + image inputs and 128K context

GPT-4o (“o” for omni) is OpenAI’s fast, high-intelligence GPT model for general tasks. It accepts text and image inputs and returns text outputs (including structured outputs) via the Chat Completions API. It supports cached prompts, batch processing, fine-tuning, and snapshots, with a 128K context window and up to 16,384 output tokens. Knowledge cutoff: Oct 1, 2023.

Aider

✓

Open-source terminal pair programmer with git-native workflows

Aider (v0.86.1) is an open-source AI pair programming tool that runs in the terminal and keeps your workflow inside git. It can automatically create sensible commits, apply diff-based edits across multiple files, and map your repository to work on large projects. Aider works best with Claude 3.7 Sonnet, DeepSeek R1/V3, OpenAI GPT-4.1 and o3/o4-mini, and Gemini 2.5 Pro, while also supporting many other cloud and local models (via OpenRouter, Ollama, and direct API keys).

Amazon Q Developer

✓

Agentic AWS-aware coding assistant with IDE, CLI, and console coverage

Amazon Q Developer (formerly CodeWhisperer) is AWS’s generative AI assistant for coding, application upgrades, and cloud operations. It provides agentic chat in IDEs, the AWS Console, chat apps, and the CLI (upgradeable to the Kiro CLI) to accelerate coding, run secure code scans and tests, and transform Java/.NET applications with guided upgrade workflows. The perpetual Free tier includes 50 agentic requests and 1,000 lines of code transformations per month; Pro is $19/user/month with higher limits, pooled upgrade quotas, admin controls, and IP indemnity.

Claude 3.5 Sonnet

✓

Mid-tier Claude model with 200K context for coding and agentic workflows

Claude 3.5 Sonnet (launched Aug 28, 2025) is Anthropic's flagship mid-tier model with a 200K context window, strong coding and vision performance, and pay-per-use pricing at $3 per 1M input tokens and $15 per 1M output tokens. It is available via Claude.ai, the Claude iOS app, the Anthropic API, Amazon Bedrock, and Google Vertex AI, supports tool use/function calling, and powers agentic workflows, RAG, and coding assistants.

Claude 4.5 Haiku

✓

Fast Claude 4.5 model with 200K context at $1/$5 per MTok

Claude 4.5 Haiku (released Oct 15, 2025) is Anthropic's fastest Claude 4.5 model with near-Sonnet 4 performance at one-third the cost. It supports a 200K token context window, extended thinking, context awareness, and full tool use (code execution, computer use, bash, text editor, web search). It is available on Claude.ai (web, iOS, Android), the Claude Developer Platform/API, Claude Code, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry with $1/$5 per million input/output token pricing.

AutoGen

✓

Open-source multi-agent framework (Python/.NET) with AgentChat and Studio

AutoGen is Microsoft's open-source framework for building agentic applications with your own model API keys. The current stable release (python v0.7.5, Sep 30 2025) ships a layered architecture: Core for event-driven message passing across Python and .NET runtimes, AgentChat for common multi-agent patterns, Extensions for model/tool connectors (OpenAI and Azure OpenAI, Anthropic, Gemini via OpenAI-compatible endpoints, and local models via Ollama), plus AutoGen Studio for no-code multi-agent prototyping and AutoGen Bench for evaluation. It's MIT-licensed and maintained in the open on GitHub.

Bolt.new

✓

AI web and app builder with tokens-based plans, hosting, and databases

Bolt.new is an AI-powered builder from StackBlitz that generates and edits production-grade web/apps in the browser. It provides hosted previews, databases, auth, custom domains, and team controls. Pricing is token-based: Free (300K/day, 1M/month), Pro (starts at 10M/month), Teams ($30/member/month), and Enterprise with SSO/audit/security. Built on WebContainers with live previews and deploys via Bolt Cloud.

Anthropic Claude API

✓

Build with Claude Opus 4.5, Sonnet 4.5, and Haiku 4.5 via the Anthropic API

The Anthropic Claude API provides pay-per-use access to Claude’s latest models: Opus 4.5 ($5/$25 MTok), Sonnet 4.5 ($3/$15 MTok for ≤200K prompts; $6/$22.5 MTok for >200K prompts), and Haiku 4.5 ($1/$5 MTok). The API supports 200K-token contexts, tool use/function calling, prompt caching (write/read discounts), and batch processing (50% savings). Available through the Claude Developer Platform with official SDKs, plus partner access on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry.

Claude Code

✓

Anthropic’s coding companion for terminal and desktop, powered by Claude Opus 4.5

Claude Code is Anthropic’s terminal-first coding experience available in Claude desktop/web and CLI. It uses Claude Opus 4.5 (and Sonnet 4.5 where applicable) to work across your local repositories with project context via CLAUDE.md, multi-file edits, code search, and permissioned command execution. Included with Claude Pro, Max, Team, and Enterprise plans; API usage is billed separately per model pricing.

Claude Opus 4.5

✓

Hybrid reasoning model for coding, agents, and computer use with a 200K context window

Claude Opus 4.5 (released Nov 24, 2025) is Anthropic's frontier model for complex coding, agentic workflows, and computer-use tasks. It offers a 200K token context window, supports tool use/function calling, and is available in Claude Pro/Max/Team/Enterprise as well as the Claude API, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. Pricing starts at $5 per 1M input tokens and $25 per 1M output tokens, with prompt caching and batch options for additional savings.

Amazon CodeWhisperer

✓

Superseded by Amazon Q Developer for code generation, chat, and security scans

CodeWhisperer is no longer offered as a standalone product. AWS merged its completions, chat, and security scanning into Amazon Q Developer for VS Code, JetBrains, and CLI. New users should install Amazon Q Developer (Free or Pro), which now carries the CodeWhisperer functionality and billing.

CrewAI

✓

MIT-licensed agents, crews, and flows framework with optional control plane

CrewAI is an MIT-licensed Python framework for multi-agent automations. The 1.6.1 release (Nov 29 2025) ships Crews for autonomous collaboration and Flows for event-driven orchestration with guardrails, memory, knowledge, and observability hooks. It runs with your own model/API keys (OpenAI/Azure OpenAI, Anthropic, OpenAI-compatible providers like Groq, or local via Ollama/LM Studio) and offers an optional Crew Control Plane for hosted/on-prem tracing, triggers, and RBAC.

DeepSeek Coder

✓

Open-source MoE coding model (V2) with 128K context

DeepSeek Coder V2 is an open Mixture-of-Experts coding model (16B Lite and 236B) with a 128K context window and support for 338 programming languages. Weights are published on Hugging Face for self-hosting; code is MIT-licensed and the model weights use the DeepSeek Model License. Hosted inference is available through the DeepSeek API using OpenAI-compatible endpoints.

Google Gemini API

✓

Access Gemini 3 Pro preview and 2.5 family via pay-as-you-go with tools, caching, and Live API

The Gemini API exposes multimodal Gemini 3 Pro preview, Gemini 2.5 Pro, 2.5 Flash, and 2.5 Flash-Lite with text, image, audio, and video support. Developers get OpenAI-compatible endpoints, tool use (Search, Maps, code execution, URL, File Search, computer-use), context caching, Batch API, and a Live streaming API. Free tier offers limited usage; paid tier is per-token with higher limits and content not used to improve models.

Gemini 3 Pro

✓

Google's multimodal reasoning model (preview)

Gemini 3 Pro is Google's preview multimodal reasoning model for the Gemini API. It supports 1M token inputs with up to 64K output tokens, handles text, images, PDFs, and video, and adds thinking levels, thought signatures, and grounded tool use for agentic coding and planning workflows.

LangChain & LangGraph

✓

LangChain for LLM apps; LangGraph for stateful graph agents

LangChain provides provider-agnostic LLM tooling, while LangGraph adds a graph-based runtime for controllable, stateful agents with human-in-the-loop, persistence, and streaming. Both are open source with Python/JS SDKs and a growing ecosystem of integrations and middleware.

Lovable

✓

Chat-based app builder with remixable templates and hosted previews

Lovable (formerly GPT Engineer) lets you build and remix web apps through chat and templates, then preview and deploy from the browser. A gallery of user-built projects showcases remix counts; pricing is not publicly listed, and users join via sign-in to start building.

Mintlify

✓

Docs platform with AI assist, portals, and SSO for teams

Mintlify is a hosted documentation platform with AI-assisted writing, search, analytics, and developer portal features. It supports custom domains, SSO on higher tiers, and integrations with GitHub/GitLab. Pricing details are not fully public; plans are listed as Free/Pro/Enterprise with AI assistant and writing agent on paid tiers.

Mutable AI (Acquired)

✓

Discontinued; technology acquired by Google

Mutable AI (known for Auto Wiki) was acquired by Google and rolled into internal code documentation efforts. The standalone product is no longer available for new signups.

Phind

✓

Developer-focused answer engine with search + chat

Phind combines live web search with LLM reasoning to answer developer questions with citations. It offers a VS Code extension and web app; pricing details are not publicly listed on the main site as of this update.

Pieces for Developers

✓

Local-first snippet manager with AI assist and cross-tool integrations

Pieces for Developers captures code snippets, screenshots, and workflow context locally, making them searchable and reusable with AI-assisted enrichment. It offers desktop apps plus IDE/browser integrations, with optional cloud LLMs and team features on paid plans.

Project IDX (now Firebase Studio)

✓

Firebase Studio: agentic cloud IDE with Gemini in Firebase and free workspaces

Project IDX has been folded into Firebase Studio, an agentic browser IDE with Gemini in Firebase for coding, debugging, testing, and refactoring. The preview is no-cost with 3 workspaces per user; Google Developer Program members get 10 (Standard) or 30 (Premium). App Prototyping and Code Assist agents, built-in previews/emulators, Git imports, and App Hosting deployments are included; some Firebase services bill separately once linked to Cloud Billing.

Replit

✓

AI-first cloud IDE with Replit Agent, Core/Teams credits, and one-click app hosting

Replit is a browser-based IDE with Replit Agent for autonomous edits, chat, and code generation. Core and Teams plans bundle monthly credits for compute, databases, and AI. Build and deploy full-stack apps with connectors, auth, storage, and security scanning straight from the workspace—no setup required.

StarCoder 2

✓

State-of-the-art open-access code LLM by BigCode

StarCoder 2 is an open-access code LLM family (3B/7B/15B) from BigCode (Hugging Face & ServiceNow), trained on The Stack v2. Weights are released under OpenRAIL-M for local or hosted inference.

Stenography

✓

AI code explanation via VS Code and Chrome extensions

Stenography explains code snippets in plain English from VS Code and Chrome. A passthrough API option minimizes code storage. Pricing on the public site is not listed as of this update; users sign in to access current limits and plans.

Supermaven

✓

Fast AI code completions with 1M-token context on Pro/Team

Supermaven delivers fast code completions and chat across VS Code, JetBrains, and Neovim. The Pro and Team tiers unlock a 1 million token context window, larger models, and monthly chat credits; Free includes core completions. Teams get centralized billing and user management.

Sweep AI

✓

Open-source GitHub app that plans fixes and opens pull requests

Sweep AI reads your repo, plans changes from GitHub issues, and opens pull requests for review. It focuses on maintenance, bug fixes, refactors, and small feature requests, with self-hosting via the open-source repo and paid cloud options available through the vendor.

Tabnine

✓

Agentic AI coding platform with private deployment and org-native context

Tabnine is an enterprise AI coding platform that delivers completions, chat, and workflow agents with strict privacy. It supports SaaS, VPC, on-prem, and air-gapped deployments, plugs into MCP tools (Git, tests, Jira, Confluence, databases), and can run customer-selected LLMs. Pricing is $59/user/month on annual contracts, with Tabnine-provided LLM usage billed at provider rates plus a 5% handling fee.

v0

✓

Generative UI builder with credits-based plans, Vercel deploys, and v0 Agent API

v0 by Vercel generates and edits React UIs from prompts with Tailwind/shadcn patterns, design mode, Figma import, GitHub sync, and one-click deploys to Vercel. Pricing is credits-based: Free ($5 monthly credits, 7 messages/day), Premium $20 with more credits and larger attachments, Team $30/user, Business $80/user with training opt-out, and Enterprise with SAML/SLAs. The v0 Agent API offers v0 Agent and v0-1.5 models with per-token pricing.

Vercel AI SDK

✓

Open-source TypeScript toolkit for streaming LLM apps with providers, tools, and generative UI

Vercel AI SDK (v6 beta) is a free, open-source toolkit for building streaming AI apps across Next.js, React, Vue/Nuxt, SvelteKit, and Node/Edge runtimes. It provides a unified provider API, tool calling, structured outputs (`generateObject`), server actions/RSC hooks, and generative UI helpers like `streamUI`, with adapters for OpenAI, Anthropic, Google, Mistral, Ollama, and more.

Warp Terminal

✓

Agentic terminal with credits-based plans, agents 3.0, and SOC2/SSO on business

Warp is a modern terminal with AI agents, code-aware blocks, and collaboration. Free includes limited credits and frontier model access; Build starts at $20/month with 1,500 AI credits and BYO key; Business $50/user/month adds SOC 2, SAML SSO, and enforced ZDR. Agents 3.0 run in-terminal and via Slack/Linear; Warp Drive syncs objects and prompts across teams.

Gemini Code Assist

✓

Google Cloud's AI coding assistant with 1M-context and terminal agent

Gemini Code Assist (formerly Duet AI) is Google Cloud's AI coding assistant for teams. Standard and Enterprise licenses bring Gemini models with a 1M-token context window to IDEs and the terminal, plus optional agent mode. Enterprise adds private code customization, expanded Google Cloud integrations, and preview access to new Gemini models via release channels.

Cursor

✓

The AI-first code editor built to make you extraordinarily productive

Cursor is an AI-powered code editor built on a fork of VS Code. It lets you write, edit, and chat about your code with frontier AI models like GPT-4.1, Claude 3.5 Sonnet, and Gemini 2.5 Pro. Cursor integrates AI directly into the editor with features like Tab (autocomplete), Composer (multi-file editing), and Agent (autonomous tasks), enabling a flow state where you can build software faster than ever before.

Devin AI

✓

AI software engineer with ticket-to-PR automation

Devin is Cognition's agentic coding platform that turns Slack/Linear/Jira tickets into tested pull requests, with a web IDE (shell/editor/browser), knowledge/playbooks, and APIs for automation.

GitHub Copilot

✓

AI pair programmer built into GitHub and popular IDEs

GitHub Copilot delivers inline code completions, chat, and pull request assistance powered by OpenAI GPT-4-class models with GitHub-native context. It works in VS Code, Visual Studio, JetBrains IDEs, Neovim, GitHub.com, and the Copilot CLI. Individuals get a 30-day free trial, and verified students, teachers, and maintainers can use Copilot for free; paid plans cover individuals, businesses, and enterprises.

GPT-5

✓

OpenAI reasoning model with 400K context and text+image inputs

GPT-5 is OpenAI’s previous-generation reasoning model for coding and agentic tasks. It supports text and image inputs with up to 128K output tokens inside a 400K context window, runs across the Chat Completions, Responses, Realtime, and Assistants APIs, and supports tools like web search, file search, image generation, and code interpreter (no computer-use). OpenAI recommends GPT-5.1 for the newest capabilities, but GPT-5 remains available for production workloads.

Windsurf

✓

AI-native IDE from Codeium with SWE-1.5 and Fast Context

Windsurf is an AI IDE from Codeium (Exafunction) that combines the Windsurf Editor, Cascade agentic chat, and Fast Context retrieval to work across large codebases. It ships Codeium’s own SWE-1.5 fast agentic model and SWE-1, plus BYOK access to major providers (OpenAI, Anthropic Claude, Google Gemini, xAI) inside the editor. Features include AI Codemaps for visual navigation, deep multi-file understanding, and enterprise controls for teams.