> For the complete documentation index, see [llms.txt](https://infronai.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://infronai.gitbook.io/docs/overview/free-models.md).

# Free Models

Infron offers free variants of selected models. Free variants carry the **`:free` suffix** (for example `deepseek/deepseek-v4-flash:free`) and are billed at **$0.00 per token**. Requests to free models **never deduct from your credit balance**.

There are two kinds of free access, with different rules:

|                                                                         | Balance required     | Daily request limit                                         | Availability                                  |
| ----------------------------------------------------------------------- | -------------------- | ----------------------------------------------------------- | --------------------------------------------- |
| **Limited-time promotions** (currently `qwen/qwen3.8-max-preview:free`) | Any positive balance | 5 request per min                                           | **Time-limited** — see promotion period below |
| **Standard free models** (all other `:free` models)                     | $5 or more           | 50 requests per day, shared across all standard free models | Ongoing, lineup changes over time             |

Your balance is required as an anti-abuse measure only — free-model usage is never charged against it.

### Limited-Time Promotion: Qwen3.8 Max Preview

> **Promotion period: now through July 28, 2026, 11:59 PM Pacific Time (UTC-7).**&#x20;

During the promotion, `qwen/qwen3.8-max-preview:free` is free with **no daily request limit**. Any account with a **positive credit balance** can use it — top up any amount to unlock it.

Model specs:

* **1M token context window**, up to 64K output tokens
* Tool calling, streaming, and JSON mode supported
* Served with **zero data retention**

```bash
curl https://llm.onerouter.pro/v1/chat/completions \
  -H "Authorization: Bearer $INFRON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-max-preview:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

### Standard Free Models

All other `:free` models follow the standard rules:

* Your account balance must be **$5 or more**. The balance is not consumed by free usage.
* **50 requests per day per account**, shared across all standard free models combined — not 50 per model.
* The daily counter resets at **00:00 UTC**.
* Default per-account rate limits still apply.

To list the current free lineup, fetch the models API and look for the `:free` suffix:

```bash
curl https://llm.onerouter.pro/v1/models \
  -H "Authorization: Bearer $INFRON_API_KEY"
```

The lineup changes over time. When a model's free variant is part of a limited-time promotion, its time window is stated on this page.

### Troubleshooting

| Error message                                                                         | What it means                                                                                                  | What to do                                                                               |
| ------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| `Free model requires account balance greater than $4.999999.`                         | Your balance is below the $5 required for standard free models.                                                | Top up to $5 or more. Your balance will not be consumed by free usage.                   |
| `Your current credits have been used up and we are unable to process further rquests` | Your account has no positive balance. New accounts start at $0, so this can appear on your very first request. | Add credits — any amount for the promotional model, $5 or more for the full free lineup. |
| `Free model daily limit exceeded (50 requests per day)`                               | You have used the shared daily pool across standard free models.                                               | Wait for the 00:00 UTC reset, use the promotional model, or use the paid variant.        |
| `Request rate increased too quickly`                                                  | Per-account rate limit — unrelated to the free-model daily pool.                                               | Slow your request rate and retry with backoff.                                           |

### Important Notes

* Free-model usage is billed at $0.00 and never deducts credits. The balance requirements above exist to prevent abuse.
* Promotions are **time-limited**. The promotion period is always stated on this page; outside that window the promotional model follows whatever rules are listed here at the time.
* Free variants may route to different providers than their paid counterparts and are served from a shared public resource pool, without SLA.
* If you have questions about free access, reach out at <support@infron.ai>.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://infronai.gitbook.io/docs/overview/free-models.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
