---
title: "Jetstream2 LLM Inference Service free inference"
description: "No-cost research and development inference across 3 models; not unrestricted production use."
canonical_url: "https://freeinferencing.com/provider/jetstream2_llm/"
md_url: "https://freeinferencing.com/provider/jetstream2_llm.md"
last_updated: "2026-09-19"
---

# Jetstream2 LLM Inference Service

> No-cost research and development inference across 3 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://llm.jetstream-cloud.org/api/`

## Models mentioned

- `llama-4-scout`
- `gpt-oss-120b`
- `muse-glimmer`

## Limits and terms

```yaml
api_usage: unlimited_fair_use
consumes_jetstream_service_units: false
availability: evolving_no_SLA
```

## What happens to your prompts?

**Partially private.** Jetstream2 excludes AI training and data mining, but chat history exists, administrators may inspect interactions for acceptable-use enforcement, and optional web search discloses selected text.

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: Jetstream2 OpenWebUI/API and direct network-restricted inference routes.
  prompt_retention: Inference stays at Indiana University and is not used for AI
    training; OpenWebUI retains unbacked-up user chat history without a fixed
    TTL.
  response_retention: Saved OpenWebUI responses follow chat-history behavior;
    direct endpoint payload retention is not separately quantified.
  ordinary_logging: Aggregate metadata is reported; exact API log fields and
    retention are not enumerated.
  model_training: User data is not used for AI training or data mining.
  product_improvement: Aggregate metadata may support operations; no content-reuse right is stated.
  human_or_operator_access: Administrators may inspect interactions for acceptable-use compliance.
  subprocessors_and_routing: Core inference is local to IU; optional web search
    sends selected material to DuckDuckGo.
  deletion_controls: Users can manage chat history, but a complete
    deletion/backup-erasure schedule is not published.
```

## Eligibility

```yaml
account_required: true
identity: ACCESS account
permitted_use: research_education_or_learning
```

## API compatibility and modalities

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

## Before you build with Jetstream2 LLM Inference Service

### 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 3 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 Jetstream2 excludes AI training and data mining, but chat history exists, administrators may inspect interactions for acceptable-use enforcement, and optional web search discloses selected text. 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 3 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

- [Inference service overview](https://docs.jetstream-cloud.org/inference-service/overview/): Official Docs
- [API access](https://docs.jetstream-cloud.org/inference-service/api/): Official Docs
- [LLM inference service update](https://jetstream-cloud.org/news-events/news/25-07-02_llm-inference-service-update.html): Official News

## Sitemap

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