PegaFlow External KV Cache for vLLM
PegaFlow external KV cache helps vLLM serving teams preserve and share KV cache across restarts, instances, and RDMA nodes.
Run Harbor Agent Evaluations on Novita Agent Sandbox
Harbor Novita Agent Sandbox support is visible on Harbor main. Learn the release boundary before using it in agent evaluations.
How to Use Novita AI with Goose: 200+ LLM Models
Configure Novita AI as a native provider in Goose. Access 200+ open-source models at $0.02/M tokens for agentic coding workflows.
Best Text-to-Speech APIs in 2026: 8 Providers Compared
Compare the best TTS APIs in 2026 — Fish Audio, ElevenLabs, OpenAI, Azure, Google, and more. Real pricing, code examples, and honest use-case picks.
DeepSeek-V4-Pro on Novita AI: 1M Context, #1 LiveCodeBench Score
DeepSeek-V4-Pro is a 1.6T-parameter open-source MoE model delivering 1 LiveCodeBench score (93.5) and 1M-token context. Available now via Novita AI.
DeepSeek-V4-Flash on Novita AI: Fast Reasoning at Lower Cost
DeepSeek-V4-Flash is now available via Novita AI. 284B MoE model, 1M token context, selectable reasoning modes. $0.14/M input. OpenAI-compatible API.
Ling-2.6-1T on Novita AI: Free API, SWE-Bench SOTA, 1T Param Model
Ling-2.6-1T is Ant Group's trillion-scale model built on MLA + Hybrid Linear Attention — not standard MoE. It achieves open-source SOTA on agent benchmarks (SWE-bench, BFCLv4, TAU2
Which Inference Provider Is Right for AI Agents
AI agents have different infrastructure needs than chatbots. Learn the 5 criteria — tool calling, context, burst traffic, cold start, concurrency
Ling-2.6-flash on Novita AI: 340 Tokens/s, ~7x Token Efficiency
Ling-2.6-flash is a 104B MoE model (7.4B active) delivering 340 tokens/s and 7x better token efficiency than Nemotron-3-Super on agent benchmarks. Available now via OpenRouter with
Top Inference API Providers for Open-Source Models in 2026
Compare top inference API providers for open-source models: pricing, model coverage, and output quality across Novita AI, Together AI, Fireworks, DeepInfra, and Groq.
Kimi K2.6 on Novita AI: API Pricing ($0.95/$4.00), SWE-Bench & Agentic Coding
Kimi K2.6 is now on Novita AI. 1T MoE open-source model, 256K context, 58.6% SWE-Bench Pro — built for long-horizon agentic coding. Try free via OpenAI-compatible API.
Qwen 3.5 Medium Series VRAM Requirements: 27B, 35B, 122B GPU Deployment Guide
Master Qwen 3.5 Medium deployment: VRAM needs, quantization options & GPU setup on Novita AI—start in minutes
Kling 3.0 Now on Novita AI: Cinematic AI Video Generation at Scale
Kling v3.0 is now live on Novita AI. Generate 3-15s AI videos with native audio, multi-shot composition, and transparent per-second pricing. Standard from $0.168/s, Pro from $0.224
Top 8 AI Inference Platforms in 2026
Discover the top 8 AI inference platforms in 2026. Compare features, pricing, and performance of leading providers like Novita AI, Together AI, and Groq.