---
title: "ScaleDown task-specific SLM API free inference"
description: "50M tokens for new accounts; it does not recur. See verified limits, model IDs, privacy terms, and primary sources for ScaleDown task-specific SLM API."
canonical_url: "https://freeinferencing.com/provider/scaledown_slm_api/"
md_url: "https://freeinferencing.com/provider/scaledown_slm_api.md"
last_updated: "2026-10-06"
---

# ScaleDown task-specific SLM API

> 50M tokens for new accounts; it does not recur.

## Classification

- **Directory:** Current
- **Free access:** One-time trial
- **Status:** Available now
- **Confidence:** High
- **Payment card:** No
- **Account:** Required
- **Equivalent paid value:** $2.50 once
- **API endpoint:** `https://api.scaledown.xyz`

## Models mentioned

No stable model IDs were recorded in this snapshot.

## Limits and terms

```yaml
signup_input_tokens: 50000000
expiry: not_published
requests_per_minute: not_published
token_billing: Input tokens only; outputs are not billed.
```

## What happens to your prompts?

**Private.** The automatically incorporated DPA excludes persistent inference-content retention, training, evaluation and secondary use; metadata is separately retained.

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: All inference requests, including the signup trial; DPA incorporated
    automatically.
  prompt_retention: In-memory inference only; no durable storage, logging or persistent cache.
  response_retention: Discarded after transmission.
  ordinary_logging: Content-free operational records, at most 90 days absent legal obligations.
  model_training: Prohibited, including anonymized content, evaluation,
    fine-tuning and feedback loops.
  product_improvement: No secondary content use or customer-traffic training signal.
  human_or_operator_access: Inference infrastructure personnel under
    confidentiality; content unavailable to development, sales and product
    teams.
  subprocessors_and_routing: US-only inference on AWS, GCP or Modal; Supabase
    holds account/billing data, not inference content.
  deletion_controls: No stored inference content to delete; separate account privacy rights apply.
agreements:
  terms_of_service: https://scaledown.ai/terms/
  privacy_policy: https://scaledown.ai/privacy/
  data_processing_addendum: https://scaledown.ai/dpa/
```

## Eligibility

```yaml
account_required: true
payment_method_required: not_stated
usage_restrictions: Trial is for evaluation/testing; general service license is
  internal business use. Resale and competing-product/model development require
  authorization.
```

## API compatibility and modalities

- **Compatibility:** Native Task Specific Rest
- **Modalities:** Model inference


## Before you build with ScaleDown task-specific SLM API

### Read the classification narrowly

This record describes the bounded offer supported by evidence on 2026-10-06; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “One-time trial” 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

No stable model ID is recorded. Resolve the current machine-readable ID, endpoint, authentication method, and request shape from the provider's live documentation before writing fixed production configuration.

### 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 **Private** because The automatically incorporated DPA excludes persistent inference-content retention, training, evaluation and secondary use; metadata is separately retained. 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 6 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

- [ScaleDown signup allowance and input-token pricing](https://scaledown.ai/): Official Pricing
- [ScaleDown hosted SLM quickstart](https://docs.scaledown.ai/quickstart): Official Docs
- [ScaleDown Terms of Service, July 20 2026](https://scaledown.ai/terms/): Official Terms
- [ScaleDown zero-retention DPA, July 20 2026](https://scaledown.ai/dpa/): Official Dpa
- [ScaleDown Privacy Policy](https://scaledown.ai/privacy/): Official Privacy
- [ScaleDown API integration repository](https://github.com/scaledown-team/scaledown): Official Repository

## Sitemap

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