---
title: "Taiwan ADI Computing Power Program free inference"
description: "A finite allowance for new accounts; it does not recur."
canonical_url: "https://freeinferencing.com/provider/taiwan_adi_ai_power/"
md_url: "https://freeinferencing.com/provider/taiwan_adi_ai_power.md"
last_updated: "2026-09-19"
---

# Taiwan ADI Computing Power Program

> A finite allowance for new accounts; it does not recur.

## Classification

- **Directory:** Current
- **Free access:** One-time trial
- **Status:** Restricted access
- **Confidence:** High
- **Payment card:** Unknown
- **Account:** Not documented
- **Equivalent paid value:** Not quantifiable


## Models mentioned

- `Llama-3.1-TAIDE-LX-8B-Chat`
- `Llama3.1-FFM-8B`
- `Gemma-4-26B-A4B`
- `Gemma-4-E2B`
- `Gemma-4-E4B`
- `Llama3.2-FFM-11B`
- `Meta-Llama-3.2-11B`
- `Phi-4-Reasoning-Plus-14B`
- `Phi-4-Reasoning-14B`
- `Llama-4-Maverick-17B`
- `Llama-4-Scout-17B`
- `Magistral-Small-2506`
- `GPT-OSS-20B`
- `Nemotron-Super-49B-v1`
- `TAME-Llama3-Taiwan-70B`
- `FoxBrain-70B`
- `FFM-70B`
- `Meta-Llama-3.3-70B`
- `GPT-OSS-120B`
- `Gemma-4-31B`
- `YOLO`
- `Whisper`
- `Taiwan-Tongues-ASR`

## Limits and terms

```yaml
award_duration_months: 3
resource_quantity: not_published
application_rounds_open_through: 2026-10-30
recurrence: false
```

## What happens to your prompts?

**Partially private.** No public award-specific policy resolves inference-content retention, training, operator access, or deletion.

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: not_found
  plan_scope: Taiwan ADI computing-power awards and award-specific inference endpoints.
  caveat: The public program/catalog surface does not specify inference retention,
    logging, training, improvement, operator access, routing, or deletion.
```

## Eligibility

```yaml
application_required: true
domestic_registered_digital_economy_business_required: true
startups_under_eight_years_priority: true
competitive_review: true
```

## API compatibility and modalities

- **Compatibility:** Program Managed Inference API
- **Modalities:** Text generation, Speech / audio
- **Geography:** Taiwan

## Before you build with Taiwan ADI Computing Power Program

### 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. “One-time trial” 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 23 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 not documented. 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 No public award-specific policy resolves inference-content retention, training, operator access, or deletion. 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 1 first-party source 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

- [ADI computing-power program](https://aipower.dginfra.gov.tw/front/index): Official Program

## Sitemap

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