Novita AI review: pricing, speed, privacy and who owns it

This page is built from Novita AI's site, docs, terms and public model list, DeepSeek's and OpenRouter's price data, Artificial Analysis measurements, Moonshot AI's K2 Vendor Verifier, Trustpilot reviews and Hacker News comments, all checked on October 21, 2026. Novita's claims are labelled as its own.

What Novita AI sells

Novita AI hosts open-weight models and sells access by the token. Its public OpenAI-compatible model list had 96 chat models on October 21, 2026: 15 from DeepSeek, 14 GLM, 14 Qwen, 8 Kimi, 5 Llama, 5 MiniMax, 4 Xiaomi MiMo and 4 Gemma, plus gpt-oss-120b and models from Tencent, Baidu and StepFun. The home page claims 200+ models, counting image, video and audio APIs such as Kling v3.0, Wan 2.7, Seedance 1.5 Pro and Fish Audio text-to-speech. Novita also rents GPU instances, serverless GPUs and agent sandboxes.

It does not resell closed models. No GPT, Claude or Gemini model appears on its pricing page, home page or model list; the only Google and OpenAI models are the open-weight Gemma and gpt-oss. Many developers use Novita without visiting it: it serves 48 models as a provider on OpenRouter and runs 36 bots on Poe.

Prices against the official APIs

Novita's pricing page says there are no hidden fees. Cached input costs about a tenth of normal input, and its batch API has an introductory 50% discount.

Novita's prices come from its pricing page. Two things stand out. Novita charges DeepSeek's peak price at all hours and does not pass on DeepSeek's off-peak half price. And its endpoints on OpenRouter were cheaper than its own list for DeepSeek V4.1 Flash and GLM 5.3, so the same model can cost less through OpenRouter. Perkstack's weekly price checks (updated July 23, 2026) found Novita tied for cheapest on small models and typically 15% to 40% above DeepInfra on large ones.

What public tests show

• Artificial Analysis measures Novita's endpoints continuously. On its Novita page (last updated September 26, 2026), DeepSeek V4.1 Flash ran at 194 tokens per second with 1.49 seconds to first chunk, and gpt-oss-120b at 219 tokens per second. On Kimi K2.6, Novita was 7th of 8 hosts at 74 tokens per second and the slowest to first chunk (3.88 seconds). On DeepSeek V4 Pro 0813 it was 6th of 10 at 70 tokens per second and 9th of 10 to first chunk (2.18 seconds).
• Moonshot AI's K2 Vendor Verifier (November 2025) replayed about 4,000 tool-calling requests against each Kimi K2 host. Novita passed on K2-0905 with 100% schema accuracy (1,299 of 1,299). On K2 Thinking it scored 72.22% trigger similarity, just under Moonshot's 73% bar, with 96.46% schema accuracy.
• OpenRouter's endpoint statistics on October 21, 2026 showed one-day uptime of 99.93% on DeepSeek V4 Pro and 100% on Kimi K2.6 and GLM 5.3. A one-day snapshot.

Novita's own home page claims 99.5% uptime.

What users report

On Hacker News, OpenRouter users mostly speak well of Novita. Comments in 2026 recommend it for production, praise its zero-retention policy and cache hit rates, and one user named it among the few OpenRouter providers that did not degrade results for them (September 29). One user running DeepSeek V4 Flash sessions of about 150,000 tokens saw about 99.5% cache hits on Novita against 99.9% on DeepSeek's own API, and occasional whitespace-counting errors only on Novita (May 25). Complaints include three of four requests failing on an old Kimi K2 model (June 27) and a quoted view that Novita hosts many models cheaply without testing them well.

Trustpilot shows 2.5 out of 5 from 9 reviews on an unclaimed profile. The 2026 one-star reviews are about the Coding Plan subscription: cancellation hard to find, credits gone in about two hours, a 40 USD charge where 20 USD was shown, and slow email support. One reviewer says a 100 USD balance is needed to run more than three GPU instances. A five-star review calls Novita "by far the best OpenRouter provider for some models".

MCP, Agent Skills and coding agents

• MCP: Novita publishes @novitalabs/novita-mcp-server in its GitHub organization. It is in beta and only manages GPU instances, templates, registry credentials and network storage; it does not call models. No MCP pass-through in API requests is documented. Novita Connect's page says MCP servers keep working when agents run on Novita models.
• Agent Skills: The novitalabs/novita-skills repository holds SKILL.md skills: novita-ai (models, GPUs, sandbox, integrations, troubleshooting), novita-sandbox and a brand design skill, installed with npx skills add novitalabs/novita-skills. It does not name the agents it targets.
• Coding agents: Claude Code connects through the Anthropic-compatible endpoint at https://api.novita.ai/anthropic; the guide's example uses Kimi K2 and does not list supported models or features. Novita Connect, a beta CLI called novi for macOS and Linux, starts Claude Code, Codex, OpenCode, Pi and DeepSeek Harness on Novita models without touching your own settings. There is also a Cursor guide.
• API formats: OpenAI-compatible chat, completions, embeddings, rerank and batch at https://api.novita.ai/openai, with guides for function calling, structured outputs, reasoning and prompt caching. The Responses format and web search are not in its docs index.
• SDKs and frameworks: guides for LangChain, LiteLLM, the OpenAI Agents SDK and Dify, a sandbox SDK and CLI, and an llms.txt for its docs.

Privacy, terms and who runs it

Section 10.2 of Novita's terms adopts a "Zero Data Retention" policy: content is not logged for human review or kept beyond producing the output unless law or support needs it, and it is not used to train Novita's models by default. Standard Compute's provider listing reads zero retention as the default, and records the inference location as not disclosed with no region pinning. The privacy policy (May 13, 2026) allows transfers to the US and elsewhere and does not say where inference runs. The site footer shows a SOC 2 badge.

The terms and privacy policy name no legal entity or address; the terms follow Delaware law. Job listings point to San Francisco, while other listings cite Hong Kong or Singapore, and no funding round was found. Fees are non-refundable except for verified Novita outages, billing errors or legal requirements claimed within 30 days. Manual top-ups must be more than 10 USD, paid through Stripe. There is no public status page; the FAQ says to ask on Discord.

How it compares with Chutes, Atlas Cloud and OpenRouter

• Chutes sells Kimi K2.6 at 0.45 / 1.95 USD, about half Novita's price, on anonymous operators' GPUs in trusted execution environments, but OpenRouter showed it at 86% to 91% one-day uptime on some models.
• Atlas Cloud also hosts open models and adds Claude, GPT, Gemini and media models; on OpenRouter it was cheaper than Novita on DeepSeek V4.1 Flash (0.135 / 0.54 USD).
• OpenRouter routes across Novita and other hosts with fallbacks and adds a 5.5% fee on credit purchases.

Who should skip it

Skip Novita AI if you need GPT, Claude or Gemini, a named company to contract with, refunds, or the lowest first-token latency on large models. It fits developers who want zero-retention access to new open models, directly or as a pinned OpenRouter provider.