# GLM-4.7-Flash-NVFP4-TEE

> GLM-4.7-Flash NVFP4 — 30B MoE, 3B active, tools + reasoning, MIT

This file is intended for AI coding agents wiring an application to this specific Chutes model.

## Important URLs

- Model page: https://chutes.ai/app/chute/vonkaiser-glm-4-7-flash-nvfp4-tee
- Model llms.txt: https://chutes.ai/app/chute/vonkaiser-glm-4-7-flash-nvfp4-tee/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/vonkaiser-glm-4-7-flash-nvfp4-tee/openapi.json
- Global Chutes llms.txt: https://chutes.ai/llms.txt
- Full Chutes docs export: https://chutes.ai/llms-full.txt
- Management API OpenAPI (account/billing/keys, NOT this model): https://api.chutes.ai/openapi.json

## Model Identifiers

- Name: `GLM-4.7-Flash-NVFP4-TEE`
- Chute ID: `0754972a-019d-5d9e-bfc3-fb1c8e8df36c`
- Slug: `vonkaiser-glm-4-7-flash-nvfp4-tee`
- Owner: `vonkaiser`

## Authentication

- Use `Authorization: Bearer $CHUTES_API_KEY` for inference calls.
- Send JSON request bodies with `Content-Type: application/json` unless the endpoint documentation says otherwise.
- The request body is FLAT — send the request fields at the top level (no `input_args`/`args` wrapper).
- This model is served on the shared OpenAI-compatible gateway. Set the request `model` field to the exact Name above (`GLM-4.7-Flash-NVFP4-TEE`), and use base URL `https://llm.chutes.ai/v1`.
- For base64 media fields, send raw base64 strings in API requests. The web playground may use temporary Blob upload references internally for large files before proxying to Chutes.

## Pricing

- $0.0245 input / $0.0978 output per 1M tokens
- $0.00245 cached input per 1M tokens
- Check the model page for current pricing.

## Endpoints

### 1. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: null.
- `stop` (string, optional)
- `min_p` (number, optional) Default: 0.
- `model` (string, required)
- `top_k` (integer, optional) Default: -1.
- `top_p` (number, optional) - Z.ai general sampling. Default 0.95. Default: 0.95.
- `stream` (boolean, optional) Default: false.
- `best_of` (integer, optional) Default: null.
- `logprobs` (boolean, optional) Default: false.
- `messages` (array, required)
- `ignore_eos` (boolean, optional) Default: false.
- `logit_bias` (object, optional) Default: null.
- `max_tokens` (integer, optional) - Max generated tokens (think + answer). Default 4096; hard-capped at 8192 for single-GPU product latency. Default: 4096.
- `min_tokens` (integer, optional) Default: 0.
- `temperature` (number, optional) - Z.ai general sampling. Default 1.0. Default: 1.
- `top_logprobs` (integer, optional) Default: 0.
- `length_penalty` (number, optional) Default: 1.
- `stop_token_ids` (array, optional)
- `enable_thinking` (boolean, optional) - Thinking/reasoning mode. Always a JSON bool; default true (GLM card). Off: answer in content with no reasoning outline. On: fill reasoning content until the model emits </think . Default: true.
- `prompt_logprobs` (integer, optional) Default: null.
- `response_format` (object, optional) Default: null.
- `use_beam_search` (boolean, optional) Default: false.
- `presence_penalty` (number, optional) - Must stay 0. Repeat penalty loops GLM-4.7-Flash. Default: 0.
- `frequency_penalty` (number, optional) - Must stay 0. Repeat penalty loops GLM-4.7-Flash. Default: 0.
- `repetition_penalty` (number, optional) - Must stay 1.0 (off). Any other value loops GLM-4.7-Flash. Default: 1.
- `skip_special_tokens` (boolean, optional) Default: true.
- `include_stop_str_in_output` (boolean, optional) Default: false.
- `spaces_between_special_tokens` (boolean, optional) Default: true.

Example call:

cURL:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "GLM-4.7-Flash-NVFP4-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

Python:

```python
import os
import requests

api_key = os.environ.get("CHUTES_API_KEY")
if not api_key:
    raise ValueError("Missing CHUTES_API_KEY")

url = "https://llm.chutes.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}
data = {
    "model": "GLM-4.7-Flash-NVFP4-TEE",
    "messages": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ],
    "stream": True,
    "max_tokens": 1024,
    "temperature": 0.7
}

import json

response = requests.request("POST", url, headers=headers, json=data, stream=True)
response.raise_for_status()

for line in response.iter_lines():
    if not line:
        continue
    line = line.decode("utf-8")
    if not line.startswith("data: "):
        continue
    chunk = line[6:]
    if chunk == "[DONE]":
        break
    try:
        choices = json.loads(chunk).get("choices") or []
    except json.JSONDecodeError:
        continue
    if not choices:
        continue
    content = choices[0].get("delta", {}).get("content")
    if content:
        print(content, end="", flush=True)
print()
```

### 2. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: null.
- `stop` (string, optional)
- `min_p` (number, optional) Default: 0.
- `model` (string, required)
- `top_k` (integer, optional) Default: -1.
- `top_p` (number, optional) Default: 1.
- `prompt` (string, required)
- `stream` (boolean, optional) Default: false.
- `best_of` (integer, optional) Default: null.
- `logprobs` (boolean, optional) Default: false.
- `ignore_eos` (boolean, optional) Default: false.
- `logit_bias` (object, optional) Default: null.
- `max_tokens` (integer, optional) Default: null.
- `min_tokens` (integer, optional) Default: 0.
- `temperature` (number, optional) Default: 0.7.
- `top_logprobs` (integer, optional) Default: 0.
- `length_penalty` (number, optional) Default: 1.
- `stop_token_ids` (array, optional)
- `prompt_logprobs` (integer, optional) Default: null.
- `response_format` (object, optional) Default: null.
- `use_beam_search` (boolean, optional) Default: false.
- `presence_penalty` (number, optional) Default: 0.
- `frequency_penalty` (number, optional) Default: 0.
- `repetition_penalty` (number, optional) Default: 1.
- `skip_special_tokens` (boolean, optional) Default: true.
- `include_stop_str_in_output` (boolean, optional) Default: false.
- `spaces_between_special_tokens` (boolean, optional) Default: true.

Example call:

cURL:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "GLM-4.7-Flash-NVFP4-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

Python:

```python
import os
import requests

api_key = os.environ.get("CHUTES_API_KEY")
if not api_key:
    raise ValueError("Missing CHUTES_API_KEY")

url = "https://llm.chutes.ai/v1/completions"
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}
data = {
    "seed": 42,
    "model": "GLM-4.7-Flash-NVFP4-TEE",
    "prompt": "a serene mountain lake at sunset",
    "stream": False,
    "max_tokens": 1024,
    "temperature": 0.7,
    "min_p": 0,
    "top_k": -1,
    "top_p": 1,
    "logprobs": False,
    "ignore_eos": False,
    "min_tokens": 0,
    "top_logprobs": 0,
    "length_penalty": 1,
    "use_beam_search": False,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "repetition_penalty": 1,
    "skip_special_tokens": True,
    "include_stop_str_in_output": False,
    "spaces_between_special_tokens": True
}

response = requests.request("POST", url, headers=headers, json=data)
response.raise_for_status()

result = response.json()
print(result)
```

### 3. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: null.
- `stop` (string, optional)
- `min_p` (number, optional) Default: 0.
- `model` (string, required)
- `top_k` (integer, optional) Default: -1.
- `top_p` (number, optional) - Z.ai general sampling. Default 0.95. Default: 0.95.
- `stream` (boolean, optional) Default: false.
- `best_of` (integer, optional) Default: null.
- `logprobs` (boolean, optional) Default: false.
- `messages` (array, required)
- `ignore_eos` (boolean, optional) Default: false.
- `logit_bias` (object, optional) Default: null.
- `max_tokens` (integer, optional) - Max generated tokens (think + answer). Default 4096; hard-capped at 8192 for single-GPU product latency. Default: 4096.
- `min_tokens` (integer, optional) Default: 0.
- `temperature` (number, optional) - Z.ai general sampling. Default 1.0. Default: 1.
- `top_logprobs` (integer, optional) Default: 0.
- `length_penalty` (number, optional) Default: 1.
- `stop_token_ids` (array, optional)
- `enable_thinking` (boolean, optional) - Thinking/reasoning mode. Always a JSON bool; default true (GLM card). Off: answer in content with no reasoning outline. On: fill reasoning content until the model emits </think . Default: true.
- `prompt_logprobs` (integer, optional) Default: null.
- `response_format` (object, optional) Default: null.
- `use_beam_search` (boolean, optional) Default: false.
- `presence_penalty` (number, optional) - Must stay 0. Repeat penalty loops GLM-4.7-Flash. Default: 0.
- `frequency_penalty` (number, optional) - Must stay 0. Repeat penalty loops GLM-4.7-Flash. Default: 0.
- `repetition_penalty` (number, optional) - Must stay 1.0 (off). Any other value loops GLM-4.7-Flash. Default: 1.
- `skip_special_tokens` (boolean, optional) Default: true.
- `include_stop_str_in_output` (boolean, optional) Default: false.
- `spaces_between_special_tokens` (boolean, optional) Default: true.

Example call:

cURL:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "GLM-4.7-Flash-NVFP4-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

Python:

```python
import os
import requests

api_key = os.environ.get("CHUTES_API_KEY")
if not api_key:
    raise ValueError("Missing CHUTES_API_KEY")

url = "https://llm.chutes.ai/v1/chat/completions"
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}
data = {
    "model": "GLM-4.7-Flash-NVFP4-TEE",
    "messages": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ],
    "stream": False,
    "max_tokens": 1024,
    "temperature": 0.7
}

response = requests.request("POST", url, headers=headers, json=data)
response.raise_for_status()

result = response.json()
print(result)
```

### 4. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: null.
- `stop` (string, optional)
- `min_p` (number, optional) Default: 0.
- `model` (string, required)
- `top_k` (integer, optional) Default: -1.
- `top_p` (number, optional) Default: 1.
- `prompt` (string, required)
- `stream` (boolean, optional) Default: false.
- `best_of` (integer, optional) Default: null.
- `logprobs` (boolean, optional) Default: false.
- `ignore_eos` (boolean, optional) Default: false.
- `logit_bias` (object, optional) Default: null.
- `max_tokens` (integer, optional) Default: null.
- `min_tokens` (integer, optional) Default: 0.
- `temperature` (number, optional) Default: 0.7.
- `top_logprobs` (integer, optional) Default: 0.
- `length_penalty` (number, optional) Default: 1.
- `stop_token_ids` (array, optional)
- `prompt_logprobs` (integer, optional) Default: null.
- `response_format` (object, optional) Default: null.
- `use_beam_search` (boolean, optional) Default: false.
- `presence_penalty` (number, optional) Default: 0.
- `frequency_penalty` (number, optional) Default: 0.
- `repetition_penalty` (number, optional) Default: 1.
- `skip_special_tokens` (boolean, optional) Default: true.
- `include_stop_str_in_output` (boolean, optional) Default: false.
- `spaces_between_special_tokens` (boolean, optional) Default: true.

Example call:

cURL:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "GLM-4.7-Flash-NVFP4-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

Python:

```python
import os
import requests

api_key = os.environ.get("CHUTES_API_KEY")
if not api_key:
    raise ValueError("Missing CHUTES_API_KEY")

url = "https://llm.chutes.ai/v1/completions"
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}
data = {
    "seed": 42,
    "model": "GLM-4.7-Flash-NVFP4-TEE",
    "prompt": "a serene mountain lake at sunset",
    "stream": False,
    "max_tokens": 1024,
    "temperature": 0.7,
    "min_p": 0,
    "top_k": -1,
    "top_p": 1,
    "logprobs": False,
    "ignore_eos": False,
    "min_tokens": 0,
    "top_logprobs": 0,
    "length_penalty": 1,
    "use_beam_search": False,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "repetition_penalty": 1,
    "skip_special_tokens": True,
    "include_stop_str_in_output": False,
    "spaces_between_special_tokens": True
}

response = requests.request("POST", url, headers=headers, json=data)
response.raise_for_status()

result = response.json()
print(result)
```

### 5. GET /v1/models

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:


Example call:

cURL:

```bash
curl -X GET "https://llm.chutes.ai/v1/models" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```

Python:

```python
import os
import requests

api_key = os.environ.get("CHUTES_API_KEY")
if not api_key:
    raise ValueError("Missing CHUTES_API_KEY")

url = "https://llm.chutes.ai/v1/models"
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}
data = {}

response = requests.request("GET", url, headers=headers, json=data)
response.raise_for_status()

result = response.json()
print(result)
```

## Agent Integration Checklist

- Pick the endpoint path that matches the desired task.
- Set `CHUTES_API_KEY` in the server-side environment only.
- Validate required fields before sending requests.
- For media models, keep file upload, base64 conversion, and output preview/download handling explicit in the app UI.