# Novita AI > A low-cost inference cloud with 200+ open models across text, image, video and speech. Canonical: https://www.subconscious.dev/providers/novita-ai · By The Subconscious Team · Updated September 30, 2026 - Founded: 2023 - Example models: DeepSeek V4 Pro, Gemma 4 - Website: https://novita.ai ## Overview Novita AI is a San Francisco inference cloud founded in late 2023 by Frank Lewis and Junyu Huang, and it competes on price and breadth. Its serverless API covers 200+ open models across LLMs, image, video, speech, voice cloning and embeddings, with LLM prices starting at $0.02 per million tokens. The API speaks both OpenAI and Anthropic formats. It became an official Hugging Face Inference Partner in April 2026 and was the day-zero launch partner for Google's Gemma 4. Next to the API sits a GPU cloud with on-demand instances from RTX 3090s to H200s, serverless GPU that scales to zero, bare metal clusters and spot pricing up to 50% off. Dedicated endpoints run any Hugging Face model, private or gated, with hot-swappable LoRA adapters and a 99.5% SLA. In April 2026 Novita added an Agent Sandbox on Firecracker microVMs, billed per second. It distributes through OpenRouter and Vercel, and it reached its scale largely bootstrapped with a small team. ## Upsides - Cheaper than Fireworks on most shared models, plus batch at 50% off. - Unusually wide multimodal catalog with day-zero support for new open models. ## Core use cases - Cost-first LLM and image generation for indie products and prototypes. - Teams that want model APIs, GPUs and agent sandboxes on one bill. ## Downsides - Looser serverless SLAs, middling uptime ratings and Discord-based support. - No public SOC 2, HIPAA or VPC peering, which rules it out for many enterprise buyers. ## At a glance | Attribute | Value | |---|---| | Model access | Open weights | | Flagship models | DeepSeek V4 Pro, Gemma 4 | | Speed | ~36 tok/s on DeepSeek V4 Pro | | Price | From $0.02 per 1M; batch 50% off | | Customization | Hot-swappable LoRA adapters | | Deployment | Serverless, GPU cloud, dedicated | | Long context | Full 1M on DeepSeek V4 Pro | ## FAQ ### What is Novita AI? Novita AI is a San Francisco inference cloud founded in late 2023 by Frank Lewis and Junyu Huang, and it competes on price and breadth. Its serverless API covers 200+ open models across LLMs, image, video, speech, voice cloning and embeddings, with LLM prices starting at $0.02 per million tokens. The API speaks both OpenAI and Anthropic formats. It became an official Hugging Face Inference Partner in April 2026 and was the day-zero launch partner for Google's Gemma 4. ### What is Novita AI best for? Cost-first LLM and image generation for indie products and prototypes; Teams that want model APIs, GPUs and agent sandboxes on one bill. ### How much does Novita AI cost? Novita AI pricing at a glance: From $0.02 per 1M; batch 50% off. Rates change often, so check Novita AI's pricing page before committing. ### How much context does Novita AI support? Novita AI's long-context support: Full 1M on DeepSeek V4 Pro. ### What are the downsides of Novita AI? Looser serverless SLAs, middling uptime ratings and Discord-based support; No public SOC 2, HIPAA or VPC peering, which rules it out for many enterprise buyers. ### What are the best alternatives to Novita AI? Common alternatives include Subconscious, OpenAI, Anthropic, Google Vertex AI, Amazon Bedrock. Each has a head-to-head comparison with Novita AI on this site. ## Comparisons - [Subconscious vs Novita AI](https://www.subconscious.dev/compare/subconscious-vs-novita-ai.md) - [OpenAI vs Novita AI](https://www.subconscious.dev/compare/openai-vs-novita-ai.md) - [Anthropic vs Novita AI](https://www.subconscious.dev/compare/anthropic-vs-novita-ai.md) - [Google Vertex AI vs Novita AI](https://www.subconscious.dev/compare/google-vertex-vs-novita-ai.md) - [Amazon Bedrock vs Novita AI](https://www.subconscious.dev/compare/aws-bedrock-vs-novita-ai.md) - [Together AI vs Novita AI](https://www.subconscious.dev/compare/together-ai-vs-novita-ai.md) - [Fireworks AI vs Novita AI](https://www.subconscious.dev/compare/fireworks-vs-novita-ai.md) - [Baseten vs Novita AI](https://www.subconscious.dev/compare/baseten-vs-novita-ai.md) - [Groq vs Novita AI](https://www.subconscious.dev/compare/groq-vs-novita-ai.md) - [Cerebras vs Novita AI](https://www.subconscious.dev/compare/cerebras-vs-novita-ai.md) - [DeepInfra vs Novita AI](https://www.subconscious.dev/compare/deepinfra-vs-novita-ai.md) - [Modal vs Novita AI](https://www.subconscious.dev/compare/modal-vs-novita-ai.md) - [xAI vs Novita AI](https://www.subconscious.dev/compare/xai-vs-novita-ai.md) - [DeepSeek vs Novita AI](https://www.subconscious.dev/compare/deepseek-vs-novita-ai.md) - [Moonshot AI vs Novita AI](https://www.subconscious.dev/compare/moonshot-ai-vs-novita-ai.md) - [Z.ai vs Novita AI](https://www.subconscious.dev/compare/z-ai-vs-novita-ai.md) - [Alibaba Cloud vs Novita AI](https://www.subconscious.dev/compare/alibaba-cloud-vs-novita-ai.md) - [Meta vs Novita AI](https://www.subconscious.dev/compare/meta-vs-novita-ai.md) - [SambaNova vs Novita AI](https://www.subconscious.dev/compare/sambanova-vs-novita-ai.md) - [Nebius vs Novita AI](https://www.subconscious.dev/compare/nebius-vs-novita-ai.md) - [fal vs Novita AI](https://www.subconscious.dev/compare/fal-vs-novita-ai.md) - [Novita AI vs Parasail](https://www.subconscious.dev/compare/novita-ai-vs-parasail.md) - [Novita AI vs Inference.net](https://www.subconscious.dev/compare/novita-ai-vs-inference-net.md) - [Novita AI vs GMI Cloud](https://www.subconscious.dev/compare/novita-ai-vs-gmi-cloud.md) - [Novita AI vs Sail Research](https://www.subconscious.dev/compare/novita-ai-vs-sail-research.md) - [Novita AI vs Morph](https://www.subconscious.dev/compare/novita-ai-vs-morph.md) - [Novita AI vs Relace](https://www.subconscious.dev/compare/novita-ai-vs-relace.md) - [Novita AI vs TypeSafe AI](https://www.subconscious.dev/compare/novita-ai-vs-typesafe-ai.md) - [Novita AI vs StepFun](https://www.subconscious.dev/compare/novita-ai-vs-stepfun.md) - [Novita AI vs Runware](https://www.subconscious.dev/compare/novita-ai-vs-runware.md) - [Novita AI vs StreamLake](https://www.subconscious.dev/compare/novita-ai-vs-streamlake.md) - [Novita AI vs Wafer](https://www.subconscious.dev/compare/novita-ai-vs-wafer.md) - [Novita AI vs RunInfra](https://www.subconscious.dev/compare/novita-ai-vs-runinfra.md) - [Novita AI vs Particle.AI](https://www.subconscious.dev/compare/novita-ai-vs-particle-ai.md) ## Sources - [Novita profile, Benched](https://benched.ai/companies/novita) - [Novita review, RecaTools](https://recatools.com/ai-directory/novita-ai/) - [Novita dedicated endpoints](https://blogs.novita.ai/best-inference-platform-for-deploying-private-generative-ai-model-endpoints/) Pricing and model lineups change often; figures are a snapshot.