> ## Documentation Index
> Fetch the complete documentation index at: https://docs.primalabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> The model catalog, pricing, and context windows.

## List models

`GET /models` returns the models **your key** can call, in the OpenAI list format, plus
each model's context window:

```bash theme={null}
curl -sS https://api.primalabs.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"
```

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "id": "primalabs-ai/DeepSeek-V4-Flash-0731",
      "object": "model",
      "owned_by": "openai",
      "max_input_tokens": 1048576
    }
  ]
}
```

| Field              | Meaning                                        |
| ------------------ | ---------------------------------------------- |
| `id`               | The model ID you pass as `model` in a request. |
| `max_input_tokens` | Context window, in tokens.                     |

Prefer this endpoint over a hard-coded list — models are added and updated over time.

## Pricing

Pricing is per token with no minimums and no reserved capacity. `GET /model/info` returns
the per-token rates for each model your key can call:

```bash theme={null}
curl -sS https://api.primalabs.ai/v1/model/info \
  -H "Authorization: Bearer YOUR_API_KEY"
```

```json theme={null}
{
  "data": [
    {
      "model_name": "primalabs-ai/DeepSeek-V4-Flash-0731",
      "model_info": {
        "max_input_tokens": 1048576,
        "input_cost_per_token": 1.4e-7,
        "output_cost_per_token": 2.8e-7,
        "cache_read_input_token_cost": 2.8e-9
      }
    }
  ]
}
```

| Field                         | Meaning                                                                                 |
| ----------------------------- | --------------------------------------------------------------------------------------- |
| `input_cost_per_token`        | Price per input (prompt) token, USD.                                                    |
| `output_cost_per_token`       | Price per output (completion) token, USD.                                               |
| `cache_read_input_token_cost` | Price per **cached** input token, USD. Prefix-cache hits are billed at this lower rate. |

Multiply by 1,000,000 for the per-million figures below.

## Current catalog

| Model                                 | Context   | Input / M | Output / M | Cached input / M |
| ------------------------------------- | --------- | --------- | ---------- | ---------------- |
| `primalabs-ai/DeepSeek-V4-Flash-0731` | 1,048,576 | \$0.14    | \$0.28     | \$0.0028         |
| `primalabs-ai/Qwen3.8-27B`            | 262,144   | \$0.425   | \$2.55     | \$0.085          |

<Info>
  Rates as of 2026-09-18. The [dashboard](https://dashboard.primalabs.ai) and
  `GET /model/info` are authoritative if this table and the API ever disagree. Live
  availability per model is on the [status page](https://status.primalabs.ai).
</Info>