NEAR AI

What is NEAR AI?

NEAR AI Cloud is a pay-per-token inference service that runs open-weight models inside hardware-secured enclaves, using Intel TDX and NVIDIA confidential GPUs. Each response carries a hardware-signed attestation that you can verify in code or with an open verifier, so you can check that the intended model and code ran in a sealed environment. The API is OpenAI-compatible: you point an existing OpenAI client at the NEAR AI base URL and keep your code. The catalog includes Qwen, GLM, Kimi and DeepSeek models, and privacy tiers are labelled per model. Teams can issue one API key per person with a spend cap. There are no subscriptions, minimums or seat licences on pay-as-you-go, and enterprise plans add reserved GPU capacity, private models, SLAs and on-prem or VPC deployment.

Use cases

• Run LLM inference on private data
• Verify AI responses with attestations
• Replace an OpenAI endpoint with open models
• Fine-tune models inside a secure enclave
• Reserve dedicated GPU capacity
• Cap spending per developer API key

Who it's for

• Developers
• Privacy-focused AI teams
• Enterprise AI teams

Why use NEAR AI

• Attestation lets you verify where your prompt ran instead of relying on a privacy policy alone.
• You can keep existing OpenAI SDK code and change only the base URL and key.
• Pay-as-you-go has no minimums, subscriptions or seat licences, and attestation is included in the token rate.
• Per-person API keys with spend caps keep team costs visible.
• Open weights and open-source tooling reduce vendor lock-in.

NEAR AI features

• Inference inside Intel TDX and NVIDIA GPU enclaves
• Hardware-signed attestation on every response
• OpenAI-compatible API
• Catalog of open-weight models with per-model pricing
• Private TEE and Private 3P TEE privacy tiers
• Per-key spend caps and usage reporting
• Dedicated deployment with reserved GPU capacity
• Private TEE fine-tuning
• Open-source runtime, verifier and enclave images

How to get started with NEAR AI

1. Generate an API key from the NEAR AI Cloud console.
2. Point an OpenAI-compatible client at the NEAR AI base URL and choose a model from the catalog.
3. Your prompt is sent over TLS and decrypted only inside the enclave, where inference runs.
4. The hardware produces an attestation tied to the code and model that served the request.
5. Check the attestation yourself, and review per-key usage and spend in the dashboard.

NEAR AI limitations

• Third-party models such as Anthropic and OpenAI models appear in an Incognito tier with no hardware privacy guarantee
• Context windows differ by model and some are small
• Enterprise pricing is quoted rather than listed

NEAR AI pricing

NEAR AI has no free plan.

NEAR AI plans

• Pay-as-you-go

  Per token, no minimums

  Priced per 1M input and output tokens by model

  • Per-token pricing on all open models
  • Hardware-signed attestation on every request
  • OpenAI-compatible API
  • No subscriptions or commitments

• Enterprise

  Custom

  • Reserved GPU capacity
  • Custom and private models
  • Volume pricing and SLAs
  • On-prem / VPC deployment options
  • Solutions engineering

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

NEAR AI alternatives

The main NEAR AI alternatives listed on Debuly are OpenRouter, Together AI, Fireworks AI, Venice.ai, Groq and FlexAI. The table compares pricing and platforms; order is A–Z.

1. 

   Fireworks AI

   Inference and training platform for open models: pay-per-token serverless APIs, GPU deployments, fine-tuning and reserved capacity.

   Developer platformsCodingAutomation and agents
   PaidVisit Fireworks AI (official site)
2. 

   FlexAI

   OpenAI-compatible inference API, dedicated GPU endpoints and fine-tuning for open models, billed per token or per GPU-hour.

   Developer platformsCoding
   PaidVisit FlexAI (official site)
3. 

   Groq

   GroqCloud inference API that serves open models such as GPT-OSS and Whisper on Groq's LPU hardware, billed per token.

   Developer platformsAudio and voiceCoding
   FreemiumVisit Groq (official site)
4. 

   OpenRouter

   Unified OpenAI-compatible API for 500+ AI models with provider fallbacks, pay-as-you-go credits and a free tier

   Developer platformsChat assistantsAutomation and agents
   FreemiumVisit OpenRouter (official site)
5. 

   Together AI

   AI cloud for running open-source models through serverless and batch inference, dedicated endpoints, GPU clusters and fine-tuning.

   Developer platformsCoding
   PaidVisit Together AI (official site)
6. 

   Venice.ai

   Venice.ai is a privacy-focused AI platform for chat, image, video, audio and code, with a free tier, paid plans and an OpenAI-compatible API.

   Chat assistantsImage generationVideoDeveloper platforms
   FreemiumVisit Venice.ai (official site)

NEAR AI FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from near.ai · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.