Novita AI Blog

See how DSpark improves Kimi-K2.6 and Kimi-K2.7-Code throughput as the speculative window scales from n=3 to n=7 in vLLM.

Novita AI's inference is now available on Opper AI's EU-hosted gateway, giving European agent builders access to 80+ open-weight models through one API.

Harbor Novita Agent Sandbox support is visible on Harbor main. Learn the release boundary before using it in agent evaluations.

Configure Novita AI as a native provider in Goose. Access 200+ open-source models at $0.02/M tokens for agentic coding workflows.

Set up Novita AI in ForgeCode to access Kimi-K2.5, GLM-5, and MiniMax-M2.5. Step-by-step guide with model comparison and pricing.

Install cli-anything-novita and give your AI agent CLI access to every model on Novita AI — DeepSeek, GLM-5, MiniMax, and more.

Unlock OpenCode's full potential with Novita AI. Step-by-step guide on how to connect DeepSeek V3.2, GLM 4.7 & more.

As the state-of-the-art GLM 4.7 model continues to lead in coding performance, Novita AI remains committed to delivering a reliable, efficient, and production-grade GLM service to

Novita AI models now available on Poe platform, expanding AI access for millions of users worldwide through integrated model deployment.

Step-by-step guide to setting up Codex CLI with Novita AI's powerful models. Configure DeepSeek, Qwen Coder, Kimi K2 for AI-powered coding.

Build intelligent Multi-Agent Systems with CrewAI and Novita's LLMs. Learn why multiple specialized AI agents outperform single-agent systems.

Integrate Novita AI with Trae IDE to access DeepSeek R1 and other cutting-edge models. Step-by-step setup guide with cost control.

We're excited to announce a strategic partnership with SGLang, a fast serving engine for large language models and vision language models.