# NVIDIA Nemotron 3.5 Super Text API

> LLM trò chuyện bằng văn bản với chế độ suy luận tùy chọn, trả về dấu vết suy luận riêng, tối đa 32,000 token

Mô hình ngôn ngữ văn bản cho các tác vụ trò chuyện và suy luận. Khi đặt `reasoning_mode` thành `think`, phản hồi gồm trường suy luận riêng trước đầu ra cuối; `no_think` trả về câu trả lời trực tiếp. `max_tokens` cho phép tối đa 32,000, `temperature` mặc định là 1 và có thể dùng `system_prompt` để định hướng hành vi.

- Model id: `nvidia/nemotron-3-5-super/text`
- Made by: NVIDIA
- Category: LLM
- Output: text
- Estimated price per run: $0.01 / run (cheapest run $0.01 (10 API credits))
- Run: `POST https://api.doitong.com/v1/run/nvidia/nemotron-3-5-super/text`
- Quote: `POST https://api.doitong.com/v1/quote/nvidia/nemotron-3-5-super/text`
- Docs page: https://doitong.com/vi/developers/models/nvidia/nemotron-3-5-super/text

## Pricing

Price: **$0.01 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.01 = 10 API credits (1 request × 10 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/nvidia/nemotron-3-5-super/text` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | ≥ 1 characters | Văn bản được cung cấp làm lời nhắc cho mô hình. |
| `system_prompt` |  | string \| null | no |  |  | Lời nhắc cấp hệ thống tùy chọn định hướng hành vi của mô hình. |
| `reasoning_mode` |  | enum (string) | no | `no_think` | `think`, `no_think` | Chế độ trả lời: phản hồi trực tiếp với `no_think`, hoặc câu trả lời cuối cùng có phần suy luận rõ ràng đi trước với `think`. |
| `max_tokens` |  | integer | no | `1024` | 1 – 32,000 | Giới hạn trên của số token được tạo. |
| `temperature` |  | number | no | `1` | 0 – 2 | Nhiệt độ dùng để lấy mẫu; giá trị được NVIDIA khuyến nghị cho mọi tác vụ là 1.0. |
| `top_p` |  | number | no | `0.95` | ≤ 1, > 0 | Khối lượng xác suất dùng cho lấy mẫu nucleus. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Kiểm soát việc bật kiểm tra an toàn. |

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/nvidia/nemotron-3-5-super/text?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nvidia/nemotron-3-5-super/text?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nvidia/nemotron-3-5-super/text", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "nvidia/nemotron-3-5-super/text",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "nvidia/nemotron-3-5-super/text",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 10,
    "usd": "0.01",
    "charged": 10,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "output": "Hello! How can I help?",
    "reasoning": "string",
    "finish_reason": "stop",
    "usage": {
      "input_tokens": 1,
      "output_tokens": 1
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `output` | string | Văn bản được tạo dưới dạng phản hồi. |
| `reasoning` | string \| null | Dấu vết suy luận chỉ khả dụng khi chọn chế độ `think`. |
| `finish_reason` | string | Lý do kết thúc tạo sinh. |
| `usage` | object {input_tokens, output_tokens} | Mức tiêu thụ token gắn với yêu cầu. |

## Related models

- [NVIDIA Nemotron 3.5 Super Video](https://doitong.com/developers/models/nvidia/nemotron-3-5-super/video.md) (`nvidia/nemotron-3-5-super/video`): $0.01 / 1000 tokens
- [NVIDIA Nemotron 3.5 Super Vision](https://doitong.com/developers/models/nvidia/nemotron-3-5-super/vision.md) (`nvidia/nemotron-3-5-super/vision`): $0.01 / run
- [Nemotron 3 Nano Omni](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni.md) (`nvidia/nemotron-3-nano-omni`): $0.01 / run
- [Bytedance Seed V2 Mini](https://doitong.com/developers/models/bytedance/seed/v2/mini.md) (`bytedance/seed/v2/mini`): $0.0001 / 1000 tokens
- [Fibo Edit \[Structured Instruction\]](https://doitong.com/developers/models/bria/fibo-edit/edit/structured_instruction.md) (`bria/fibo-edit/edit/structured_instruction`): $0.01 / request
- [Fibo Lite · Structured Prompt](https://doitong.com/developers/models/bria/fibo-lite/generate/structured_prompt.md) (`bria/fibo-lite/generate/structured_prompt`): $0.008 / request
- [Fibo · Structured Prompt](https://doitong.com/developers/models/bria/fibo/generate/structured_prompt.md) (`bria/fibo/generate/structured_prompt`): $0.01 / request
- [Mureka 9.5 Lyrics Generation](https://doitong.com/developers/models/mureka/api/generate/lyrics.md) (`mureka/api/generate/lyrics`): $0.0135 / request

## Links

- HTML page: https://doitong.com/developers/models/nvidia/nemotron-3-5-super/text
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=nvidia/nemotron-3-5-super/text
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/nvidia/nemotron-3-5-super/text