Каталог AI-сервисов

Kilo is an agentic engineering platform and open-source coding agent that can generate code from natural language, run terminal commands, and automate browser-based steps, available as a VS Code extension and a CLI.

DryRun Security

Security context as you code, without being a security expert.

KAT-Coder-Pro V2 is a hosted Kwaipilot coding model listed on OpenRouter with a 256,000-token context window. It is positioned as a large-context software engineering model for coding and agent-style development tasks, intended for API-based use rather than open-weight local deployment.

TuringMind AI

AI brain to unfurl code and unravel insights

CodeRocket.app

AI-Powered Tailwind Code Generation for Modern Developers

Code generator

AI coding partner for instant, clean code solutions.

Code Formatter Pro

Straightforward Python code formatter, ensuring PEP 8 compliance.

Qwen3-Coder-Next is an open-weight language model built specifically for coding agents and local development, optimized for tool use and long-horizon software engineering tasks.

Trinity Large Preview is a 400B-parameter (about 13B active) frontier Trinity MoE model with long-context comprehension, tuned for strong reasoning, coding and multi-step agents, served via hosted preview APIs.

GPT-5.2-Codex is OpenAI’s frontier agentic coding model based on GPT-5.2, optimized for long-horizon software work, large refactors and migrations, better Windows support and state-of-the-art cybersecurity performance in Codex.

SERA-32B is Ai2’s flagship 32B Open Coding Agent, a Qwen 3-32B based repository-level coding model trained with Soft Verified Generation that reaches about 49.5% on SWE-bench Verified, rivaling much larger proprietary systems.

APIPod

One API, access all top AI models.

PixVerse V5.6 is PixVerse’s latest video model, upgrading V5.5 with cinema level visuals, more natural multilingual voices, smoother physics aware motion and less warping, while keeping generation speed and cost roughly the same as earlier V5 models.

Dia-1.6B is Nari Labs’ ultra-compact instruction model—about 1.6B parameters—built for fast, low-cost deployment on a single GPU or edge device. It handles everyday reasoning, summarization, and lightweight coding, with structured JSON outputs and tool/function calling for agents.

Bugzy AI

Release faster with QA that keeps up

Gemini 3 Deep Think is Google’s specialized reasoning mode, tuned to tackle hard math, science and engineering problems by running deep, parallel chains of thought for researchers, engineers and Gemini AI Ultra subscribers.

Qwen-Coder-Qoder is a reinforced code model based on Qwen-Coder, custom trained for the Qoder agentic coding platform to improve end to end programming performance inside its IDE and CLI workflows

Web Page Design Code Generator

Turn web designs into code with AI precision.

Nemotron-3-Nano-30B-A3B is NVIDIA’s 30B-class LLM trained from scratch as a unified model for both reasoning and standard chat tasks. It can be configured to produce a reasoning trace before the final answer, letting developers switch reasoning behavior through the chat template.

Grok 4 Heavy is xAI’s most powerful Grok 4 variant—frontier-level reasoning with native tool use, real-time search, a 256K-token context window, and higher rate limits. It’s available via the SuperGrok Heavy tier and the xAI API.