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

# Models

`GET /v1/models`

I list every model my network can serve at this moment. Think of it as a live roll call rather than a catalog: I only include a model while at least one worker is hosting it.

***

## Ask me what I can run

```bash
curl https://api.theacompute.com/v1/models \
  -H "Authorization: Bearer thea_live_your_key_here"
```

### What I send back

```json
{
  "object": "list",
  "data": [
    {
      "id": "llama-3.3-70b",
      "object": "model",
      "created": 1750000000,
      "owned_by": "meta",
      "theacompute": {
        "tier": "max",
        "credits_per_request": 40,
        "credits_per_1k_tokens": 20,
        "active_workers": 12,
        "median_latency_ms": 1840,
        "parameters": "70B",
        "context_window": 128000
      }
    },
    {
      "id": "qwen3-8b",
      "object": "model",
      "created": 1750000000,
      "owned_by": "qwen",
      "theacompute": {
        "tier": "standard",
        "credits_per_request": 8,
        "credits_per_1k_tokens": 4,
        "active_workers": 47,
        "median_latency_ms": 420,
        "parameters": "8B",
        "context_window": 32768
      }
    }
  ]
}
```

On top of the standard OpenAI model schema, I attach a `theacompute` object to each entry with live data from my network. Prices are in units; my API just calls them credits, which is why the fields are named `credits_per_request` and `credits_per_1k_tokens`.

| Field                   | What I put in it                                                               |
| ----------------------- | ------------------------------------------------------------------------------ |
| `tier`                  | Which pricing tier I place the model in: `lite`, `standard`, `pro`, or `max`   |
| `credits_per_request`   | The flat price I charge for a completion of up to roughly 500 output tokens    |
| `credits_per_1k_tokens` | What I charge per 1,000 output tokens after a completion goes past that length |
| `active_workers`        | The number of workers serving this model for me at this moment                 |
| `median_latency_ms`     | The p50 time-to-first-token I measure across the current worker pool           |
| `parameters`            | How big the model is, counted in parameters                                    |
| `context_window`        | The most context, in tokens, the model will take                               |

***

## What I can run today

Here's my launch lineup. I add to it as workers bring new models online and governance signs off on them.

| Model ID        | Parameters | Context | Tier     | Units/request |
| --------------- | ---------- | ------- | -------- | ------------- |
| `llama-3.3-70b` | 70B        | 128K    | Max      | 40            |
| `deepseek-r1`   | 70B        | 128K    | Max      | 40            |
| `llama-3.2-27b` | 27B        | 128K    | Pro      | 18            |
| `qwen3-14b`     | 14B        | 32K     | Pro      | 18            |
| `qwen3-8b`      | 8B         | 32K     | Standard | 8             |
| `mistral-7b`    | 7B         | 32K     | Standard | 8             |
| `llama-3.2-3b`  | 3B         | 128K    | Lite     | 2             |
| `qwen3-1.7b`    | 1.7B       | 32K     | Lite     | 2             |

I keep model IDs stable, so go ahead and build on them. If a newer model replaces one on this list, I keep honoring the old ID until a governance vote formally retires it, and I always give advance notice before that happens.

***

## How available a model is

`active_workers` tells you how much of my network is backing a model at the moment. With a bigger pool, you'll usually see faster first tokens and fewer rejected jobs.

If you ask for a model whose worker count has fallen to zero, I respond with a `503` and a suggested `retry_after`.

While I'm in beta, I run my own seed provider pool so every launch model stays reliably available. Beta means I'm early, not half-built.

***

## Ask me about one model

```bash
curl https://api.theacompute.com/v1/models/qwen3-8b \
  -H "Authorization: Bearer thea_live_your_key_here"
```

I return a single model object with exactly the same shape as an entry in my list response. It's a handy way to check worker count and latency before you send me a job.


---

# 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://docs.theacompute.com/api-reference/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.