---
title: "National Research Platform Managed LLMs free inference"
description: "No-cost research and development inference across 10 models; not unrestricted production use."
canonical_url: "https://freeinferencing.com/provider/nsf_nrp_managed_llm/"
md_url: "https://freeinferencing.com/provider/nsf_nrp_managed_llm.md"
last_updated: "2026-09-19"
---

# National Research Platform Managed LLMs

> No-cost research and development inference across 10 models; not unrestricted production use.

## Classification

- **Directory:** Current
- **Free access:** Research / development
- **Status:** Restricted access
- **Confidence:** High
- **Payment card:** Unknown
- **Account:** Required
- **Equivalent paid value:** Not quantifiable
- **API endpoint:** `https://ellm.nrp-nautilus.io/v1`

## Models mentioned

- `qwen3`
- `qwen3-small`
- `gpt-oss`
- `gemma`
- `gemma-small`
- `kimi`
- `glm-5`
- `deepseek-v4-flash`
- `minimax-m2`
- `qwen3-embedding`

## Limits and terms

```yaml
output_tokens_per_minute_per_api_token_per_model: 200000
large_request_threshold_percent_of_context: 35
large_request_concurrency_per_user: 1
short_request_concurrency:
  - maximum: 2
    model_ids:
      - kimi
      - glm-5
      - deepseek-v4-flash
  - maximum: 8
    model_ids:
      - minimax-m2
      - qwen3-small
      - gemma
      - gemma-small
  - maximum: 16
    model_ids:
      - qwen3
      - gpt-oss
      - qwen3-embedding
enforcement: guidance_not_yet_automatic
SDSC_and_Internet2_affiliates_multiplier: 2
```

## What happens to your prompts?

**Partially private.** NRP documents user-scoped caching guidance but not an endpoint-wide retention TTL, training rule, operator-access rule, or deletion control.

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: partial
  plan_scope: NRP managed LLM inference for approved nonprofit research/education
    namespaces.
  prompt_retention: API guidance discusses optional user-isolated caching; no
    endpoint-wide default TTL is published.
  response_retention: Cached responses follow the same isolation concern; ordinary
    retention is not documented.
  ordinary_logging: Request log fields and retention are not documented.
  model_training: No public service-wide no-training commitment was found.
  product_improvement: not_documented
  human_or_operator_access: not_documented
  subprocessors_and_routing: Models are NRP-managed; tenant/cache boundaries
    matter and additional subprocessors are not enumerated.
  deletion_controls: Users can avoid or configure shared caching, but default TTL
    and deletion interfaces are unpublished.
```

## Eligibility

```yaml
account_required: true
audience: U.S. nonprofit research and education including community colleges
permitted_use: noncommercial_and_nonprofit
llm_enabled_namespace_required: true
```

## API compatibility and modalities

- **Compatibility:** OpenAI Compatible
- **Modalities:** Text generation, Embeddings
- **Geography:** United States

## Before you build with National Research Platform Managed LLMs

### 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, Unknown payment-card status, and the plan-specific sources below.

### Resolve the live model route

The snapshot records 10 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 Unknown, 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 **Partially private** because NRP documents user-scoped caching guidance but not an endpoint-wide retention TTL, training rule, operator-access rule, or deletion control. 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 4 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

- [Hosted LLMs](https://nrp.ai/llms/): Official Product
- [Models](https://nrp.ai/documentation/userdocs/ai/llm-managed/models/): Official Docs
- [API access](https://nrp.ai/documentation/userdocs/ai/llm-managed/api-access/): Official Docs
- [Fair use](https://nrp.ai/documentation/userdocs/ai/llm-managed/fair-use/): Official Docs

## Sitemap

See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.