--- title: "NVIDIA Build / NVIDIA-hosted NIM free inference" description: "No-cost research and development inference across 82 models; not unrestricted production use." canonical_url: "https://freeinferencing.com/provider/nvidia_build/" md_url: "https://freeinferencing.com/provider/nvidia_build.md" last_updated: "2026-09-19" --- # NVIDIA Build / NVIDIA-hosted NIM > No-cost research and development inference across 82 models; not unrestricted production use. ## Classification - **Directory:** Current - **Free access:** Research / development - **Status:** Available now - **Confidence:** High - **Payment card:** No - **Account:** Required - **Equivalent paid value:** Up to $1,057,314.21/mo - **API endpoint:** `https://integrate.api.nvidia.com/v1` ## Models mentioned - `01-ai/yi-large` - `adept/fuyu-8b` - `ai21labs/jamba-1.5-large-instruct` - `aisingapore/sea-lion-7b-instruct` - `bigcode/starcoder2-15b` - `databricks/dbrx-instruct` - `deepseek-ai/deepseek-coder-6.7b-instruct` - `deepseek-ai/deepseek-v4-flash-0731` - `z-ai/glm-5.3` - `google/codegemma-1.1-7b` - `google/codegemma-7b` - `google/deplot` - `google/diffusiongemma-26b-a4b-it` - `google/gemma-2b` - `google/gemma-3-12b-it` - `google/gemma-3-4b-it` - `google/gemma-4-31b-it` - `google/recurrentgemma-2b` - `ibm/granite-3.0-3b-a800m-instruct` - `ibm/granite-3.0-8b-instruct` - `ibm/granite-34b-code-instruct` - `ibm/granite-8b-code-instruct` - `meta/codellama-70b` - `meta/llama-3.2-11b-vision-instruct` - `meta/llama-3.2-90b-vision-instruct` - `meta/llama-guard-4-12b` - `meta/llama2-70b` - `meta/muse-glimmer-30b` - `microsoft/kosmos-2` - `microsoft/phi-3-vision-128k-instruct` - `microsoft/phi-3.5-moe-instruct` - `mistralai/codestral-22b-instruct-v0.1` - `mistralai/mistral-7b-instruct-v0.3` - `mistralai/mistral-large` - `mistralai/mistral-large-2-instruct` - `mistralai/mistral-nemotron` - `mistralai/mixtral-8x22b-v0.1` - `moonshotai/kimi-k2.6` - `moonshotai/kimi-k3` - `nv-mistralai/mistral-nemo-12b-instruct` - `nvidia/ai-synthetic-video-detector` - `nvidia/cosmos-reason2-8b` - `nvidia/embed-qa-4` - `nvidia/ising-calibration-1.5-31b` - `nvidia/llama-3.1-nemoguard-8b-content-safety` - `nvidia/llama-3.1-nemoguard-8b-topic-control` - `nvidia/llama-3.1-nemotron-51b-instruct` - `nvidia/llama-3.1-nemotron-70b-instruct` - `nvidia/llama-3.1-nemotron-safety-guard-8b-v3` - `nvidia/llama-3.1-nemotron-ultra-253b-v1` - `nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1` - `nvidia/llama-3.2-nv-embedqa-1b-v1` - `nvidia/llama-nemotron-embed-vl-1b-v2` - `nvidia/llama3-chatqa-1.5-70b` - `nvidia/mistral-nemo-minitron-8b-8k-instruct` - `nvidia/nemotron-3-embed-1b` - `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning` - `nvidia/nemotron-3-super-120b-a12b` - `nvidia/nemotron-3-ultra-550b-a55b` - `nvidia/nemotron-3.5-content-safety` - `nvidia/nemotron-3.5-lightning-30b-a3b` - `nvidia/nemotron-4-340b-instruct` - `nvidia/nemotron-4-340b-reward` - `nvidia/nemotron-nano-3-30b-a3b` - `nvidia/nemotron-parse` - `nvidia/nemotron-parse-2.0` - `nvidia/neva-22b` - `nvidia/nv-embedqa-mistral-7b-v2` - `nvidia/nvclip` - `nvidia/riva-translate-4b-instruct` - `nvidia/riva-translate-4b-instruct-v1.1` - `nvidia/riva-translate-4b-instruct-v2` - `nvidia/vila` - `openai/gpt-oss-20b` - `poolside/laguna-xs-2.1` - `snowflake/arctic-embed-l` - `writer/palmyra-creative-122b` - `writer/palmyra-fin-70b-32k` - `writer/palmyra-med-70b` - `writer/palmyra-med-70b-32k` - `z-ai/glm-5.3-flash` - `zyphra/zamba2-7b-instruct` ## Limits and terms ```yaml public_numeric_limits: false official_rule: Varies by model and concurrency; inspect the signed-in account. current_marketing_phrase: Unlimited prototyping allowed_use: - prototyping - research - development - testing - learning ``` ## What happens to your prompts? **Not private.** The free developer terms permit storage and broad product, service, and underlying-model improvement uses. Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data. ## Data governance and agreements ```yaml data_governance: review_status: reviewed plan_scope: NVIDIA API Catalog and NVIDIA-hosted NIM trial access under the Technology Access Terms; a model or product-specific agreement can supersede those terms. prompt_retention: No fixed prompt-retention period is promised. The terms permit NVIDIA, affiliates, and service providers to host and store User Content to provide and support the service, for security, and to improve products or underlying technology. response_retention: No inference-output-specific retention commitment was found in the governing trial terms. ordinary_logging: NVIDIA may monitor, scan, or review communications and User Content transmitted through its servers for safety, security, moderation, or legal requests. model_training: The terms do not make a narrow no-training commitment. Their User Content license permits modification and improvement of NVIDIA products, services, and underlying technology, so users should treat training or equivalent improvement use as permitted unless a product-specific agreement says otherwise. product_improvement: Expressly permitted under the User Content license. human_or_operator_access: Monitoring, scanning, and review are permitted for security, moderation, and legal purposes; service providers may process content under the license. subprocessors_and_routing: NVIDIA affiliates and service providers may process User Content, and separately identified product agreements can apply to individual models or services. deletion_controls: The terms do not guarantee permanent access or recovery if data is deleted or lost; public User Content may remain after reposting, and NVIDIA accepts no general duty to remove it. caveat: Unless a separate product agreement expressly permits it, User Content must not contain confidential information, personal data, protected health information, payment-card data, or sensitive human-subject research. This makes the free trial unsuitable for sensitive prompts. agreements: technology_access_terms: https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA_Technology_Access_TOU.pdf privacy_policy: https://www.nvidia.com/en-us/about-nvidia/privacy-policy/ ``` ## Eligibility ```yaml account_required: true developer_program_membership_required: true membership_cost_usd: 0 payment_method_required: not_documented ``` ## API compatibility and modalities - **Compatibility:** LLM NIMs Are OpenAI Compatible; Non LLM NIMs Can Use Task Specific APIs. - **Modalities:** Text generation, Embeddings, Image / vision, Video, Safety ## Before you build with NVIDIA Build / NVIDIA-hosted NIM ### Read the classification narrowly This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Research / development” should be interpreted together with the Current directory placement, High confidence, No payment-card status, and the plan-specific sources below. ### Resolve the live model route The snapshot records 82 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online. ### Match the quota to the workload shape Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms. ### Preserve billing and privacy boundaries The recorded payment-card requirement is No, and account access is required. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Not private** because The free developer terms permit storage and broad product, service, and underlying-model improvement uses. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content. ### Follow the evidence, then re-check it This record links 10 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term. ### Plan fallback without policy drift A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable. ### Monitor the offer as a dependency Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity. ### Test one complete request before scaling Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement. ## Primary sources - [NVIDIA NIM for Developers](https://developer.nvidia.com/nim): Official Product - [Run NIM Anywhere](https://docs.api.nvidia.com/nim/re/docs/run-anywhere): Official Docs - [Models endpoint](https://integrate.api.nvidia.com/v1/models): Live Catalog - [Free NIM access announcement](https://developer.nvidia.com/blog/?p=86238): Announcement - [NVIDIA Technology Access Terms of Use](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA_Technology_Access_TOU.pdf): Official Terms - [NVIDIA Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/): Official Privacy - [NVIDIA Build Kimi K3 page (free endpoint; up to 40 rpm; 10,000 requests/day; 1,048,576-token context)](https://build.nvidia.com/moonshotai/kimi-k3): Official Product - [NVIDIA Kimi K3 API reference (max\_tokens: maximum 65,536)](https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k3-infer): Official API Reference - [OpenRouter models API price for moonshotai/kimi-k3 (snapshot 2026-09-13)](https://openrouter.ai/api/v1/models): Router Pricing - [NVIDIA NIM partner adoption](https://nvidianews.nvidia.com/news/nvidia-nim-model-deployment-generative-ai-developers): Official Press Release ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.