from huggingface_hub import InferenceClient

messages = [{"role": "user", "content": "What is the Transformers library known for?"}]
client = InferenceClient("http://localhost:8000")

result = client.chat_completion(messages, model="Qwen/Qwen2.5-0.5B-Instruct", max_tokens=256)
print(result.choices[0].message.content)

The Transformers library is primarily known for its ability to create and manipulate large-scale language models [...]

from huggingface_hub import InferenceClient

messages = [{"role": "user", "content": "What is the Transformers library known for?"}]
client = InferenceClient("http://localhost:8000")

stream = client.chat_completion(messages, model="Qwen/Qwen2.5-0.5B-Instruct", max_tokens=256, stream=True)
for chunk in stream:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The Transformers library is primarily known for its ability to create and manipulate large-scale language models [...]

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "What is the Transformers library known for?"
        }
    ],
)
print(completion.choices[0].message.content)

The Transformers library is primarily known for its ability to create and manipulate large-scale language models [...]

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "What is the Transformers library known for?"
        }
    ],
    stream=True,
)

for chunk in completion:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The Transformers library is primarily known for its ability to create and manipulate large-scale language models [...]

curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "messages": [{"role": "user", "content": "What is the Transformers library known for?"}],
    "temperature": 0.9,
    "max_tokens": 256
  }'

{
  "id": "ade3578d-e2c3-47ed-b651-c014991a92f6",
  "choices": [
    {
      "finish_reason": "length",
      "index": 0,
      "message": {
        "content": "The Transformers library is primarily known for its ability to create and manipulate large-scale language models [...]",
        "role": "assistant"
      }
    }
  ],
  "created": 1776184004,
  "model": "Qwen/Qwen2.5-0.5B-Instruct@main",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 256,
    "prompt_tokens": 37,
    "total_tokens": 293
  }
}

curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "messages": [{"role": "user", "content": "What is the Transformers library known for?"}],
    "temperature": 0.9,
    "max_tokens": 256,
    "stream": true
  }'

data: {"id":"596d3941-754d-43b4-8773-9bf9940049f5","choices":[{"delta":{"role":"assistant"},"index":0}],"created":1776183469,"model":"Qwen/Qwen2.5-0.5B-Instruct@main","object":"chat.completion.chunk","system_fingerprint":""}

data: {"id":"596d3941-754d-43b4-8773-9bf9940049f5","choices":[{"delta":{"content":"The"},"index":0}],"created":1776183469,"model":"Qwen/Qwen2.5-0.5B-Instruct@main","object":"chat.completion.chunk","system_fingerprint":""}

(...)

from huggingface_hub import InferenceClient

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
                }
            },
        ],
    }
]
client = InferenceClient("http://localhost:8000")

result = client.chat_completion(messages, model="Qwen/Qwen2.5-VL-7B-Instruct", max_tokens=256)
print(result.choices[0].message.content)

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

from huggingface_hub import InferenceClient

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {
                "type": "image_url",
                "image_url": {
                    "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
                }
            },
        ],
    }
]
client = InferenceClient("http://localhost:8000")

stream = client.chat_completion(messages, model="Qwen/Qwen2.5-VL-7B-Instruct", max_tokens=256, stream=True)
for chunk in stream:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
                    }
                },
            ],
        }
    ],
)
print(completion.choices[0].message.content)

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
                    }
                },
            ],
        }
    ],
    stream=True,
)

for chunk in completion:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What's in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 256
  }'

{
  "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon [...]",
        "role": "assistant"
      }
    }
  ],
  "created": 1753366665,
  "model": "Qwen/Qwen2.5-VL-7B-Instruct@main",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 50,
    "prompt_tokens": 120,
    "total_tokens": 170
  }
}

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "stream": true,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What's in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 256
  }'

data: {"id":"f47ac10b-58cc-4372-a567-0e02b2c3d479","choices":[{"delta":{"role":"assistant"},"index":0}],"created":1753366665,"model":"Qwen/Qwen2.5-VL-7B-Instruct@main","object":"chat.completion.chunk","system_fingerprint":""}

data: {"id":"f47ac10b-58cc-4372-a567-0e02b2c3d479","choices":[{"delta":{"content":"The "},"index":0}],"created":1753366701,"model":"Qwen/Qwen2.5-VL-7B-Instruct@main","object":"chat.completion.chunk","system_fingerprint":""}

(...)

import base64
from huggingface_hub.utils import httpx
from huggingface_hub import InferenceClient

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Transcribe this audio."},
            {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
        ],
    }
]
client = InferenceClient("http://localhost:8000")

result = client.chat_completion(messages, model="google/gemma-4-E2B-it", max_tokens=256)
print(result.choices[0].message.content)

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

import base64
from huggingface_hub.utils import httpx
from huggingface_hub import InferenceClient

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Transcribe this audio."},
            {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
        ],
    }
]
client = InferenceClient("http://localhost:8000")

stream = client.chat_completion(messages, model="google/gemma-4-E2B-it", max_tokens=256, stream=True)
for chunk in stream:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

import base64
from huggingface_hub.utils import httpx
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

completion = client.chat.completions.create(
    model="google/gemma-4-E2B-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Transcribe this audio."},
                {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
            ],
        }
    ],
)
print(completion.choices[0].message.content)

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

import base64
from huggingface_hub.utils import httpx
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

completion = client.chat.completions.create(
    model="google/gemma-4-E2B-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Transcribe this audio."},
                {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
            ],
        }
    ],
    stream=True,
)

for chunk in completion:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

# First, base64-encode the audio file and build the JSON payload
AUDIO_B64=$(curl -sL https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3 | base64 -w 0)

cat <<EOF > /tmp/audio_request.json
{
  "model": "google/gemma-4-E2B-it",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "Transcribe this audio."},
        {"type": "input_audio", "input_audio": {"data": "$AUDIO_B64", "format": "mp3"}}
      ]
    }
  ]
}
EOF

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d @/tmp/audio_request.json

{
  "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "This week, I traveled to Chicago to deliver my final farewell address to the nation [...]",
        "role": "assistant"
      }
    }
  ],
  "created": 1753366665,
  "model": "google/gemma-4-E2B-it@main",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 85,
    "prompt_tokens": 200,
    "total_tokens": 285
  }
}

# First, base64-encode the audio file and build the JSON payload
AUDIO_B64=$(curl -sL https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3 | base64 -w 0)

cat <<EOF > /tmp/audio_request.json
{
  "model": "google/gemma-4-E2B-it",
  "stream": true,
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "Transcribe this audio."},
        {"type": "input_audio", "input_audio": {"data": "$AUDIO_B64", "format": "mp3"}}
      ]
    }
  ]
}
EOF

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d @/tmp/audio_request.json

data: {"id":"cb997e1d-98b9-414a-be89-1880288610ef","choices":[{"delta":{"role":"assistant"},"index":0}],"created":1776254856,"model":"google/gemma-4-E2B-it@main","object":"chat.completion.chunk","system_fingerprint":""}

data: {"id":"cb997e1d-98b9-414a-be89-1880288610ef","choices":[{"delta":{"content":"This"},"index":0}],"created":1776254856,"model":"google/gemma-4-E2B-it@main","object":"chat.completion.chunk","system_fingerprint":""}

(...)

from huggingface_hub import InferenceClient

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
            {"type": "text", "text": "What is happening in the video and what is the song about?"},
        ],
    }
]
client = InferenceClient("http://localhost:8000")

result = client.chat_completion(messages, model="google/gemma-4-E2B-it", max_tokens=256)
print(result.choices[0].message.content)

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

from huggingface_hub import InferenceClient

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
            {"type": "text", "text": "What is happening in the video and what is the song about?"},
        ],
    }
]
client = InferenceClient("http://localhost:8000")

stream = client.chat_completion(messages, model="google/gemma-4-E2B-it", max_tokens=256, stream=True)
for chunk in stream:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="google/gemma-4-E2B-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
                {"type": "text", "text": "What is happening in the video and what is the song about?"},
            ],
        }
    ],
    max_tokens=256,
)
print(completion.choices[0].message.content)

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

completion = client.chat.completions.create(
    model="google/gemma-4-E2B-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
                {"type": "text", "text": "What is happening in the video and what is the song about?"},
            ],
        }
    ],
    max_tokens=256,
    stream=True,
)

for chunk in completion:
    token = chunk.choices[0].delta.content
    if token:
        print(token, end="")

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-E2B-it",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
          {"type": "text", "text": "What is happening in the video and what is the song about?"}
        ]
      }
    ],
    "max_tokens": 256
  }'

{
  "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
  "choices": [
    {
      "finish_reason": "length",
      "index": 0,
      "message": {
        "content": "The video captures a live music performance at a music festival or a large concert [...]",
        "role": "assistant"
      }
    }
  ],
  "created": 1753366665,
  "model": "google/gemma-4-E2B-it@main",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 256,
    "prompt_tokens": 350,
    "total_tokens": 606
  }
}

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-E2B-it",
    "stream": true,
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
          {"type": "text", "text": "What is happening in the video and what is the song about?"}
        ]
      }
    ],
    "max_tokens": 256
  }'

data: {"id":"cb997e1d-98b9-414a-be89-1880288610ef","choices":[{"delta":{"role":"assistant"},"index":0}],"created":1776254856,"model":"google/gemma-4-E2B-it@main","object":"chat.completion.chunk","system_fingerprint":""}

data: {"id":"cb997e1d-98b9-414a-be89-1880288610ef","choices":[{"delta":{"content":"Based"},"index":0}],"created":1776254856,"model":"google/gemma-4-E2B-it@main","object":"chat.completion.chunk","system_fingerprint":""}

(...)

curl -X POST http://localhost:8000/v1/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-0.5B",
    "prompt": "The capital of France is",
    "max_tokens": 20
  }'

{
  "id": "chatcmpl-abc123",
  "object": "text_completion",
  "created": 1234567890,
  "model": "Qwen/Qwen2.5-0.5B@main",
  "choices": [
    {
      "text": " Paris, and the capital of the United States is Washington, D.C.",
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 16,
    "total_tokens": 21
  }
}

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

# Non-streaming
completion = client.completions.create(
    model="Qwen/Qwen2.5-0.5B",
    prompt="The capital of France is",
    max_tokens=20,
)
print(completion.choices[0].text)

 Paris, and the capital of the United States is Washington, D.C.

stream = client.completions.create(
    model="Qwen/Qwen2.5-0.5B",
    prompt="The capital of France is",
    max_tokens=20,
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].text, end="")

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=256,
    stream=False,
)
print(response.output[0].content[0].text)

Once upon a time, in a faraway land, there lived a beautiful unicorn named Luna [...]

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="Qwen/Qwen2.5-0.5B-Instruct",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=256,
    stream=True,
)

for event in response:
    if hasattr(event, "delta") and event.delta:
        print(event.delta, end="")

Once upon a time, in a faraway land, there lived a beautiful unicorn named Luna [...]

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "input": "Tell me a three sentence bedtime story about a unicorn.",
    "max_output_tokens": 256,
    "stream": false
  }'

{
  "id": "resp_8693af9b-b561-4267-bd1a-22d1b43284cb",
  "created_at": 1776258580.7114341,
  "model": "Qwen/Qwen2.5-0.5B-Instruct@main",
  "object": "response",
  "output": [
    {
      "id": "msg_8693af9b-b561-4267-bd1a-22d1b43284cb",
      "content": [
        {
          "annotations": [],
          "text": "Once upon a time, in a faraway land, there lived a beautiful unicorn named Luna [...]",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed"
}

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "stream": true,
    "input": "Tell me a three sentence bedtime story about a unicorn.",
    "max_output_tokens": 256
  }'

data: {"response":{"id":"resp_req_0","created_at":1754059817.783648,"model":"Qwen/Qwen2.5-0.5B-Instruct@main","object":"response","output":[],"status":"queued"},"sequence_number":0,"type":"response.created"}

data: {"content_index":0,"delta":"Once ","item_id":"msg_req_0","output_index":0,"sequence_number":5,"type":"response.output_text.delta"}

data: {"content_index":0,"delta":"upon ","item_id":"msg_req_0","output_index":0,"sequence_number":6,"type":"response.output_text.delta"}

(...)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    input=[
        {"type": "input_text", "text": "What's in this image?"},
        {
            "type": "input_image",
            "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
        },
    ],
    max_output_tokens=256,
    stream=False,
)
print(response.output[0].content[0].text)

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="Qwen/Qwen2.5-VL-7B-Instruct",
    input=[
        {"type": "input_text", "text": "What's in this image?"},
        {
            "type": "input_image",
            "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg",
        },
    ],
    max_output_tokens=256,
    stream=True,
)

for event in response:
    if hasattr(event, "delta") and event.delta:
        print(event.delta, end="")

The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon, given the barren, rocky landscape and the dark sky in the background. The astronaut is holding a large egg that has cracked open, revealing a small creature inside. The scene is imaginative and playful, combining elements of space exploration with a whimsical twist involving the egg and the creature.

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "input": [
      {"type": "input_text", "text": "What'\''s in this image?"},
      {"type": "input_image", "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"}
    ],
    "max_output_tokens": 256,
    "stream": false
  }'

{
  "id": "resp_f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "created_at": 1776258580.7114341,
  "model": "Qwen/Qwen2.5-VL-7B-Instruct@main",
  "object": "response",
  "output": [
    {
      "id": "msg_f47ac10b-58cc-4372-a567-0e02b2c3d479",
      "content": [
        {
          "annotations": [],
          "text": "The image depicts an astronaut in a space suit standing on what appears to be the surface of the moon [...]",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed"
}

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-VL-7B-Instruct",
    "stream": true,
    "input": [
      {"type": "input_text", "text": "What'\''s in this image?"},
      {"type": "input_image", "image_url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"}
    ],
    "max_output_tokens": 256
  }'

data: {"response":{"id":"resp_f47ac10b-58cc-4372-a567-0e02b2c3d479","created_at":1776258580.7114341,"model":"Qwen/Qwen2.5-VL-7B-Instruct@main","object":"response","output":[],"status":"queued"},"sequence_number":0,"type":"response.created"}

data: {"content_index":0,"delta":"The ","item_id":"msg_f47ac10b","output_index":0,"sequence_number":5,"type":"response.output_text.delta"}

(...)

import base64
from huggingface_hub.utils import httpx
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

response = client.responses.create(
    model="google/gemma-4-E2B-it",
    input=[
        {"type": "input_text", "text": "Transcribe this audio."},
        {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
    ],
    max_output_tokens=256,
    stream=False,
)
print(response.output[0].content[0].text)

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

import base64
from huggingface_hub.utils import httpx
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

audio_url = "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3"
audio_b64 = base64.b64encode(httpx.get(audio_url, follow_redirects=True).content).decode()

response = client.responses.create(
    model="google/gemma-4-E2B-it",
    input=[
        {"type": "input_text", "text": "Transcribe this audio."},
        {"type": "input_audio", "input_audio": {"data": audio_b64, "format": "mp3"}},
            ],
        }
    ],
    max_output_tokens=256,
    stream=True,
)

for event in response:
    if hasattr(event, "delta") and event.delta:
        print(event.delta, end="")

This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was an opportunity to say thank you. Whether we've seen eye to eye or rarely agreed at all, my conversations with you, the American people, in living rooms and schools, at farms and on factory floors, at diners, and on distant military outposts, all these conversations are what have kept me honest.

# First, base64-encode the audio file and build the JSON payload
AUDIO_B64=$(curl -sL https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3 | base64 -w 0)

cat <<EOF > /tmp/audio_request.json
{
  "model": "google/gemma-4-E2B-it",
  "input": [
    {"type": "input_text", "text": "Transcribe this audio."},
    {"type": "input_audio", "input_audio": {"data": "$AUDIO_B64", "format": "mp3"}}
  ],
  "max_output_tokens": 256,
  "stream": false
}
EOF

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d @/tmp/audio_request.json

{
  "id": "resp_a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "created_at": 1776258580.7114341,
  "model": "google/gemma-4-E2B-it@main",
  "object": "response",
  "output": [
    {
      "id": "msg_a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "content": [
        {
          "annotations": [],
          "text": "This week, I traveled to Chicago to deliver my final farewell address to the nation [...]",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed"
}

# First, base64-encode the audio file and build the JSON payload
AUDIO_B64=$(curl -sL https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama_first_45_secs.mp3 | base64 -w 0)

cat <<EOF > /tmp/audio_request.json
{
  "model": "google/gemma-4-E2B-it",
  "stream": true,
  "input": [
    {"type": "input_text", "text": "Transcribe this audio."},
    {"type": "input_audio", "input_audio": {"data": "$AUDIO_B64", "format": "mp3"}}
  ],
  "max_output_tokens": 256
}
EOF

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d @/tmp/audio_request.json

data: {"response":{"id":"resp_a1b2c3d4-e5f6-7890-abcd-ef1234567890","created_at":1776258580.7114341,"model":"google/gemma-4-E2B-it@main","object":"response","output":[],"status":"queued"},"sequence_number":0,"type":"response.created"}

data: {"content_index":0,"delta":"This ","item_id":"msg_a1b2c3d4","output_index":0,"sequence_number":5,"type":"response.output_text.delta"}

(...)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="google/gemma-4-E2B-it",
    input=[
        {"type": "input_text", "text": "What is happening in the video and what is the song about?"},
        {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
    ],
    max_output_tokens=256,
    stream=False,
)
print(response.output[0].content[0].text)

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<random_string>")

response = client.responses.create(
    model="google/gemma-4-E2B-it",
    input=[
        {"type": "input_text", "text": "What is happening in the video and what is the song about?"},
        {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}},
    ],
    max_output_tokens=256,
    stream=True,
)

for event in response:
    if hasattr(event, "delta") and event.delta:
        print(event.delta, end="")

The video captures a live music performance at a music festival or a large concert. There are several musicians on stage, including a central figure playing an acoustic guitar and singing. The foreground is filled with the backs of the audience, indicating a large crowd watching the show. The stage is dramatically lit with bright spotlights and blue and white stage lighting, with haze and smoke creating an immersive atmosphere.

The lyrics of the song are: "I don't care 'bout street, from that fresh street, 'cause there's no problem, another one I want to be, in the storm..."

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-E2B-it",
    "input": [
      {"type": "input_text", "text": "What is happening in the video and what is the song about?"},
      {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}}
    ],
    "max_output_tokens": 256,
    "stream": false
  }'

{
  "id": "resp_b2c3d4e5-f6a7-8901-bcde-f12345678901",
  "created_at": 1776258580.7114341,
  "model": "google/gemma-4-E2B-it@main",
  "object": "response",
  "output": [
    {
      "id": "msg_b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "content": [
        {
          "annotations": [],
          "text": "The video captures a live music performance at a music festival or a large concert [...]",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed"
}

curl http://localhost:8000/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-E2B-it",
    "stream": true,
    "input": [
      {"type": "input_text", "text": "What is happening in the video and what is the song about?"},
      {"type": "video_url", "video_url": {"url": "https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/concert.mp4"}}
    ],
    "max_output_tokens": 256
  }'

data: {"response":{"id":"resp_b2c3d4e5-f6a7-8901-bcde-f12345678901","created_at":1776258580.7114341,"model":"google/gemma-4-E2B-it@main","object":"response","output":[],"status":"queued"},"sequence_number":0,"type":"response.created"}

data: {"content_index":0,"delta":"Based ","item_id":"msg_b2c3d4e5","output_index":0,"sequence_number":5,"type":"response.output_text.delta"}

(...)

curl http://localhost:8000/v1/systemone \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen2.5-1.5B-Instruct",
    "state": "Our integration has been failing for 3 days and we are losing sales!",
    "questions": {
      "team": {
        "type": "choice",
        "instructions": "Which team handles this?",
        "criteria": {"billing": null, "technical": "Bugs or integration problems"}
      },
      "urgency": {
        "type": "score",
        "instructions": "How urgent is this ticket?",
        "criteria": ["low", "medium", "high"]
      },
      "upset": {"type": "noul", "instructions": "Is the customer upset?"}
    }
  }'

npm install @typesafe-ai/sdk

import { choice, noul, score, TypeSafeClient } from "@typesafe-ai/sdk";

const client = new TypeSafeClient({
  baseURL: "http://localhost:8000",
  apiKey: "<random_string>",
});

const response = await client.systemOne({
  model: "Qwen/Qwen2.5-1.5B-Instruct",
  state: "Our integration has been failing for 3 days and we are losing sales!",
  questions: {
    team: choice("Which team handles this?", {
      billing: null,
      technical: "Bugs or integration problems",
    }),
    urgency: score("How urgent is this ticket?", ["low", "medium", "high"]),
    upset: noul("Is the customer upset?"),
  },
});

console.log(response.answers.team.choice);
console.log(response.answers.urgency.score);
console.log(response.answers.upset.noul);

technical
1.6739138662815094
0.851952850818634

data: {"status": "loading", "model": "org/model@main", "stage": "processor"}
data: {"status": "loading", "model": "org/model@main", "stage": "config"}
data: {"status": "loading", "model": "org/model@main", "stage": "download", "progress": {"current": 0, "total": 269100000}}
data: {"status": "loading", "model": "org/model@main", "stage": "download", "progress": {"current": 134600000, "total": 269100000}}
data: {"status": "loading", "model": "org/model@main", "stage": "download", "progress": {"current": 269100000, "total": 269100000}}
data: {"status": "loading", "model": "org/model@main", "stage": "weights", "progress": {"current": 1, "total": 272}}
data: {"status": "loading", "model": "org/model@main", "stage": "weights", "progress": {"current": 272, "total": 272}}
data: {"status": "ready", "model": "org/model@main", "cached": false}

data: {"status": "loading", "model": "org/model@main", "stage": "processor"}
data: {"status": "loading", "model": "org/model@main", "stage": "config"}
data: {"status": "loading", "model": "org/model@main", "stage": "weights", "progress": {"current": 1, "total": 272}}
data: {"status": "loading", "model": "org/model@main", "stage": "weights", "progress": {"current": 272, "total": 272}}
data: {"status": "ready", "model": "org/model@main", "cached": false}

data: {"status": "ready", "model": "org/model@main", "cached": true}

# Model returns a tool call
messages = [{"role": "user", "content": "What's the weather like in San Francisco?"}]
response = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    messages=messages,
    tools=tools,
)
assistant_message = response.choices[0].message

# Execute the tool locally
tool_call = assistant_message.tool_calls[0]
result = {"temperature": 22, "condition": "sunny"}  # your actual function call here

# Send the tool result back
messages.append(assistant_message)
messages.append({
    "role": "tool",
    "tool_call_id": tool_call.id,
    "content": json.dumps(result),
})
final_response = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    messages=messages,
    tools=tools,
)
print(final_response.choices[0].message.content)

user_message = {"role": "user", "content": "What's the weather like in San Francisco?"}
response = client.responses.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    input=[user_message],
    tools=tools,
    stream=False,
)
tool_call = next(item for item in response.output if item.type == "function_call")

result = {"temperature": 22, "condition": "sunny"}

final_response = client.responses.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    input=[
        user_message,
        tool_call.model_dump(exclude_none=True),
        {"type": "function_call_output", "call_id": tool_call.call_id, "output": json.dumps(result)},
    ],
    tools=tools,
    stream=False,
)
print(final_response.output_text)

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="<KEY>")

completion = client.chat.completions.create(
    model="Qwen/Qwen3-1.7B",
    messages=[{"role": "user", "content": "What is 17 * 23?"}],
)
message = completion.choices[0].message
print("reasoning:", message.reasoning_content)
print("answer:", message.content)

chunks = list(
    client.chat.completions.create(
        model="Qwen/Qwen3-1.7B",
        messages=[{"role": "user", "content": "What is 17 * 23?"}],
        stream=True,
    )
)
reasoning = "".join(getattr(c.choices[0].delta, "reasoning_content", None) or "" for c in chunks)
content = "".join(c.choices[0].delta.content or "" for c in chunks)

curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-1.7B",
    "messages": [{"role": "user", "content": "What is 17 * 23?"}],
    "chat_template_kwargs": {"enable_thinking": true}
  }'

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "17 * 23 = 391.",
        "reasoning_content": "Let me compute 17 * 23. 17 * 20 = 340, 17 * 3 = 51, so 340 + 51 = 391."
      },
      "finish_reason": "stop",
      "index": 0
    }
  ]
}

response = client.responses.create(
    model="Qwen/Qwen3-1.7B",
    input="What is 17 * 23?",
    stream=False,
)
reasoning_item = next(i for i in response.output if i.type == "reasoning")
message_item = next(i for i in response.output if i.type == "message")
print("reasoning:", reasoning_item.content[0].text)
print("answer:", message_item.content[0].text)

stream = client.responses.create(
    model="Qwen/Qwen3-1.7B",
    input="What is 17 * 23?",
    stream=True,
)

for event in stream:
    if event.type == "response.reasoning_text.delta":
        print(event.delta, end="")
    elif event.type == "response.output_text.delta":
        print(event.delta, end="")

first = client.chat.completions.create(
    model="Qwen/Qwen3-1.7B",
    messages=[{"role": "user", "content": "What is 17 * 23?"}],
).choices[0].message

second = client.chat.completions.create(
    model="Qwen/Qwen3-1.7B",
    messages=[
        {"role": "user", "content": "What is 17 * 23?"},
        {
            "role": "assistant",
            "content": first.content,
            "reasoning_content": first.reasoning_content,
        },
        {"role": "user", "content": "Now multiply that result by 2."},
    ],
)
print(second.choices[0].message.content)

first = client.responses.create(
    model="Qwen/Qwen3-1.7B",
    input="What is 17 * 23?",
    stream=False,
)
reasoning_item = next(i for i in first.output if i.type == "reasoning")
message_item = next(i for i in first.output if i.type == "message")

second = client.responses.create(
    model="Qwen/Qwen3-1.7B",
    input=[
        {"role": "user", "content": "What is 17 * 23?"},
        reasoning_item.model_dump(exclude_none=True),
        {"role": "assistant", "content": message_item.content[0].text},
        {"role": "user", "content": "Now multiply that result by 2."},
    ],
    stream=False,
)
print(second.output_text)