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

# Latest Model Examples

> Examples for the latest public models based on the local model index

> Last updated: 2026-06-07

# Latest Model Examples

This page follows the public model index in `web/src/data/models/index.json`. New examples should use these models first; delisted or non-public models are not shown as copyable examples.

## Recommended Models

| Use case                           | Recommended model                                          |
| ---------------------------------- | ---------------------------------------------------------- |
| Default chat and general reasoning | `gpt-5.5`                                                  |
| Cost-sensitive chat                | `gpt-5-mini`                                               |
| Claude coding and long context     | `claude-opus-4-8`                                          |
| Hard Claude tasks                  | `claude-opus-4-8`                                          |
| Lightweight Claude tasks           | `claude-opus-4-8`                                          |
| Gemini native multimodal           | `gemini-3.1-pro`                                           |
| Low-latency Gemini                 | `gemini-3.1-flash-lite`                                    |
| DeepSeek reasoning                 | `deepseek-v4-pro`                                          |
| Fast xAI chat                      | `grok-4.1-fast`                                            |
| MiniMax long context               | `MiniMax-M2.7`                                             |
| Qwen vision                        | `qwen3-vl-235b-a22b-instruct` or `qwen2.5-vl-72b-instruct` |
| Suno music                         | `suno_music`                                               |

## Chat Completions

```bash cURL theme={null}
curl -X POST https://api.crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {"role": "user", "content": "Explain when this endpoint is useful in three sentences."}
    ]
  }'
```

## Responses API

```bash cURL theme={null}
curl -X POST https://api.crazyrouter.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-5.5",
    "input": "Create a pre-release checklist for API docs."
  }'
```

## Claude Messages

```bash cURL theme={null}
curl -X POST https://api.crazyrouter.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Review whether this API changelog is clear."}
    ]
  }'
```

## Gemini Native

```bash cURL theme={null}
curl "https://api.crazyrouter.com/v1beta/models/gemini-3.1-pro:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{"text": "Summarize the API docs checks I should run today."}]
      }
    ]
  }'
```

## Vision

```bash cURL theme={null}
curl -X POST https://api.crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen3-vl-235b-a22b-instruct",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe the key information in this image."},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}
        ]
      }
    ]
  }'
```

## Music And Lyrics

The current production model index exposes `suno_music`. Lyrics generation does not have a stable production route. For song submission, query, and continuation flows, see:

* [Suno SDK unified task guide](/en/sdks/suno-sdk)

<Note>
  Actual availability also depends on token allowlists, channel state, and platform updates. Before production rollout, call [`GET /v1/models`](/en/chat/openai/models) to confirm the model IDs visible to your token.
</Note>