> ## Documentation Index
> Fetch the complete documentation index at: https://student-213fb9fc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Available Models

> All 30+ AI models available on AJ STUDIOZ Cloud Infra

## Overview

AJ STUDIOZ Cloud Infra hosts a curated selection of frontier open-weight AI models. All models are accessible through both the [Ollama-compatible API](/api-reference/introduction) and the [OpenAI-compatible API](/api-reference/endpoint/v1-chat-completions).

<Note>
  Use the model name exactly as shown in the `model` column when making API requests.
</Note>

***

## Flagship Models (100B+)

These are the most capable models for complex reasoning, coding, and agentic tasks.

| Model Name               | Size   | Added    | Best For                    |
| ------------------------ | ------ | -------- | --------------------------- |
| `kimi-k2:1t`             | \~1.1T | Sep 2025 | Agentic tasks, long context |
| `kimi-k2.5`              | \~1.1T | Jan 2026 | Next-gen reasoning          |
| `kimi-k2-thinking`       | \~1.1T | Nov 2025 | Chain-of-thought reasoning  |
| `qwen3.5:397b`           | 397B   | Feb 2026 | Multilingual, reasoning     |
| `qwen3-coder:480b`       | 480B   | Jul 2025 | State-of-the-art coding     |
| `qwen3-vl:235b`          | 235B   | Sep 2025 | Vision + language           |
| `qwen3-vl:235b-instruct` | 235B   | Sep 2025 | Vision, instruction-tuned   |
| `cogito-2.1:671b`        | 671B   | Nov 2025 | Scientific reasoning        |
| `deepseek-v3.1:671b`     | 671B   | Nov 2025 | Coding, analysis            |
| `deepseek-v3.2`          | 671B   | Dec 2025 | Latest DeepSeek release     |
| `glm-5`                  | Large  | Feb 2026 | Long context, multilingual  |
| `glm-4.6`                | Large  | Sep 2025 | Balanced GLM model          |
| `glm-4.7`                | Large  | Dec 2025 | Latest GLM release          |
| `minimax-m2`             | 230B   | Oct 2025 | Multimodal                  |
| `minimax-m2.1`           | 230B   | Dec 2025 | Enhanced multimodal         |
| `minimax-m2.5`           | 230B   | Feb 2026 | Latest MiniMax model        |
| `mistral-large-3:675b`   | 675B   | Dec 2025 | Multilingual excellence     |

***

## Large Models (20B–100B)

High-performance models with broad capability coverage.

| Model Name             | Size  | Added    | Best For             |
| ---------------------- | ----- | -------- | -------------------- |
| `gpt-oss:120b`         | 120B  | Aug 2025 | General purpose      |
| `devstral-2:123b`      | 123B  | Dec 2025 | Code generation      |
| `qwen3-next:80b`       | 80B   | Sep 2025 | Coding + reasoning   |
| `qwen3-coder-next`     | \~82B | Feb 2025 | Advanced code tasks  |
| `gemma3:27b`           | 27B   | Mar 2025 | Balanced, fast       |
| `devstral-small-2:24b` | 24B   | Dec 2025 | Efficient code model |
| `gemma3:12b`           | 12B   | Mar 2025 | Fast inference       |
| `nemotron-3-nano:30b`  | 30B   | Dec 2025 | NVIDIA specialized   |

***

## Small & Compact Models (≤20B)

Optimized for speed, low latency, and cost efficiency.

| Model Name               | Size  | Added    | Best For               |
| ------------------------ | ----- | -------- | ---------------------- |
| `gpt-oss:20b`            | 20B   | Aug 2025 | Fast general purpose   |
| `rnj-1:8b`               | \~16B | Dec 2025 | Compact reasoning      |
| `ministral-3:14b`        | 14B   | Dec 2025 | Efficient multilingual |
| `ministral-3:8b`         | 10.4B | Dec 2025 | Balanced small model   |
| `gemma3:4b`              | 8.6B  | Mar 2025 | Ultra-fast inference   |
| `ministral-3:3b`         | 4.7B  | Dec 2025 | Fastest responses      |
| `gemini-3-flash-preview` | —     | Dec 2025 | API-based, ultra-fast  |

***

## Full Model Catalog (JSON)

<Accordion title="View raw model list (JSON)">
  ```json theme={null}
  {
    "models": [
      { "name": "gpt-oss:120b", "model": "gpt-oss:120b", "size": 65290180781, "digest": "d98fe6ba01e6" },
      { "name": "ministral-3:3b", "model": "ministral-3:3b", "size": 4670000000, "digest": "a1b2c3d40001" },
      { "name": "gemma3:4b", "model": "gemma3:4b", "size": 8600000000, "digest": "c1d2e3f40002" },
      { "name": "gemma3:27b", "model": "gemma3:27b", "size": 55000000000, "digest": "c1d2e3f40004" },
      { "name": "glm-5", "model": "glm-5", "size": 756162687872, "digest": "3f40c24f825c" },
      { "name": "kimi-k2.5", "model": "kimi-k2.5", "size": 1118481408000, "digest": "89c148d8ace8" },
      { "name": "qwen3-coder-next", "model": "qwen3-coder-next", "size": 81800000000, "digest": "d8f3c2a16e5b" },
      { "name": "ministral-3:8b", "model": "ministral-3:8b", "size": 10400000000, "digest": "a1b2c3d40003" },
      { "name": "cogito-2.1:671b", "model": "cogito-2.1:671b", "size": 688586727753, "digest": "5c1168f3a867" },
      { "name": "minimax-m2", "model": "minimax-m2", "size": 230000000000, "digest": "d46b950f79ba" },
      { "name": "devstral-2:123b", "model": "devstral-2:123b", "size": 128249391520, "digest": "de057a012512" },
      { "name": "qwen3-next:80b", "model": "qwen3-next:80b", "size": 81800000000, "digest": "aada434099ae" },
      { "name": "glm-4.6", "model": "glm-4.6", "size": 696060000000, "digest": "ee0873722cc3" },
      { "name": "glm-4.7", "model": "glm-4.7", "size": 696060000000, "digest": "8c95dad96c75" },
      { "name": "kimi-k2-thinking", "model": "kimi-k2-thinking", "size": 1118481408000, "digest": "7bb8dfabfd9c" },
      { "name": "gpt-oss:20b", "model": "gpt-oss:20b", "size": 13780162412, "digest": "05afbac4bad6" },
      { "name": "qwen3-vl:235b-instruct", "model": "qwen3-vl:235b-instruct", "size": 470000000000, "digest": "a5020f0cea71" },
      { "name": "ministral-3:14b", "model": "ministral-3:14b", "size": 15700000000, "digest": "a1b2c3d40005" },
      { "name": "devstral-small-2:24b", "model": "devstral-small-2:24b", "size": 51600000000, "digest": "de057a012512" },
      { "name": "gemini-3-flash-preview", "model": "gemini-3-flash-preview", "size": 0, "digest": "f1e2c3f40001" },
      { "name": "deepseek-v3.1:671b", "model": "deepseek-v3.1:671b", "size": 688586727753, "digest": "e1c8a9725f49" },
      { "name": "minimax-m2.5", "model": "minimax-m2.5", "size": 230000000000, "digest": "1361fbbdd94e" },
      { "name": "gemma3:12b", "model": "gemma3:12b", "size": 24000000000, "digest": "c1d2e3f40003" },
      { "name": "qwen3.5:397b", "model": "qwen3.5:397b", "size": 397000000000, "digest": "b909ca2f1b7f" },
      { "name": "kimi-k2:1t", "model": "kimi-k2:1t", "size": 1118481408000, "digest": "9665a13eb6f1" },
      { "name": "nemotron-3-nano:30b", "model": "nemotron-3-nano:30b", "size": 32645090390, "digest": "a4b4f1851393" },
      { "name": "mistral-large-3:675b", "model": "mistral-large-3:675b", "size": 682000000000, "digest": "f7e3b2a16d5c" },
      { "name": "rnj-1:8b", "model": "rnj-1:8b", "size": 16000000000, "digest": "385d8e8f6803" },
      { "name": "qwen3-coder:480b", "model": "qwen3-coder:480b", "size": 510492157952, "digest": "653ca2ec1d71" },
      { "name": "deepseek-v3.2", "model": "deepseek-v3.2", "size": 688586727753, "digest": "a403a93c7b13" },
      { "name": "qwen3-vl:235b", "model": "qwen3-vl:235b", "size": 470000000000, "digest": "d8afd22a6506" },
      { "name": "minimax-m2.1", "model": "minimax-m2.1", "size": 230000000000, "digest": "a7c3e1f98b2d" }
    ]
  }
  ```
</Accordion>

***

## Retrieve via API

You can also retrieve the model list dynamically:

```bash theme={null}
curl https://api.ajstudioz.co.in/api/tags \
  -H "Authorization: Bearer YOUR_API_KEY"
```

<Card title="List Models API Reference" icon="code" href="/api-reference/endpoint/list-models" />