National Research Platform Managed LLMs
Operated by National Research Platform
No-cost research and development inference across 10 models; not unrestricted production use.
https://ellm.nrp-nautilus.io/v1Models mentioned
qwen3qwen3-smallgpt-ossgemmagemma-smallkimiglm-5deepseek-v4-flashminimax-m2qwen3-embeddingEquivalent paid value
How this was valued: The published allowance or a defensible paid comparison is not precise enough to calculate.
NRP publishes concurrency and fair-use guidance but no finite recurring request/token allocation or same-service paid unit.
Limits and terms
- Output Tokens Per Minute Per API Token Per Model
- 200,000
- Large Request Threshold Percent Of Context
- 35
- Large Request Concurrency Per User
- 1
- Short Request Concurrency
- Maximum
- 2
- Model Ids
- kimiglm-5deepseek-v4-flash
- Maximum
- 8
- Model Ids
- minimax-m2qwen3-smallgemmagemma-small
- Maximum
- 16
- Model Ids
- qwen3gpt-ossqwen3-embedding
- Enforcement
- guidance not yet automatic
- SDSC And Internet2 Affiliates Multiplier
- 2
What happens to your prompts?
NRP documents user-scoped caching guidance but not an endpoint-wide retention TTL, training rule, operator-access rule, or deletion control.
- 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- Users can avoid or configure shared caching, but default TTL and deletion interfaces are unpublished.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
- Account Required
- Yes
- Audience
- U.S. nonprofit research and education including community colleges
- Permitted Use
- noncommercial and nonprofit
- LLM Enabled Namespace Required
- Yes
Primary sources
Before you build with National Research Platform Managed LLMs
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label 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 region.
Resolve the live model route
This snapshot records 10 model IDs. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. The recorded base endpoint is https://ellm.nrp-nautilus.io/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. The payment-card requirement is conditional or not clearly documented. Treat signup friction and billing exposure as unresolved until the account flow confirms them. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “Partially private”: NRP documents user-scoped caching guidance but not an endpoint-wide retention TTL, training rule, operator-access rule, or deletion control. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 4 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.