Tìm hiểu và tính mã thông báo

from google import genai

client = genai.Client()
model_info = client.models.get(model="gemini-2.0-flash")
print(f"{model_info.input_token_limit=}")
print(f"{model_info.output_token_limit=}")
# ( e.g., input_token_limit=30720, output_token_limit=2048 )
count_tokens.py

from google import genai

client = genai.Client()
prompt = "The quick brown fox jumps over the lazy dog."

# Count tokens using the new client method.
total_tokens = client.models.count_tokens(
    model="gemini-2.0-flash", contents=prompt
)
print("total_tokens: ", total_tokens)
# ( e.g., total_tokens: 10 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=prompt
)

# The usage_metadata provides detailed token counts.
print(response.usage_metadata)
# ( e.g., prompt_token_count: 11, candidates_token_count: 73, total_token_count: 84 )
count_tokens.py

from google import genai
from google.genai import types

client = genai.Client()

chat = client.chats.create(
    model="gemini-2.0-flash",
    history=[
        types.Content(
            role="user", parts=[types.Part(text="Hi my name is Bob")]
        ),
        types.Content(role="model", parts=[types.Part(text="Hi Bob!")]),
    ],
)
# Count tokens for the chat history.
print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=chat.get_history()
    )
)
# ( e.g., total_tokens: 10 )

response = chat.send_message(
    message="In one sentence, explain how a computer works to a young child."
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 25, candidates_token_count: 21, total_token_count: 46 )

# You can count tokens for the combined history and a new message.
extra = types.UserContent(
    parts=[
        types.Part(
            text="What is the meaning of life?",
        )
    ]
)
history = chat.get_history()
history.append(extra)
print(client.models.count_tokens(model="gemini-2.0-flash", contents=history))
# ( e.g., total_tokens: 56 )
count_tokens.py

from google import genai

client = genai.Client()
prompt = "Tell me about this image"
your_image_file = client.files.upload(file=media / "organ.jpg")

print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=[prompt, your_image_file]
    )
)
# ( e.g., total_tokens: 263 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=[prompt, your_image_file]
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 264, candidates_token_count: 80, total_token_count: 345 )
count_tokens.py

from google import genai
import PIL.Image

client = genai.Client()
prompt = "Tell me about this image"
your_image_file = PIL.Image.open(media / "organ.jpg")

# Count tokens for combined text and inline image.
print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=[prompt, your_image_file]
    )
)
# ( e.g., total_tokens: 263 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=[prompt, your_image_file]
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 264, candidates_token_count: 80, total_token_count: 345 )
count_tokens.py

from google import genai
import time

client = genai.Client()
prompt = "Tell me about this video"
your_file = client.files.upload(file=media / "Big_Buck_Bunny.mp4")

# Poll until the video file is completely processed (state becomes ACTIVE).
while not your_file.state or your_file.state.name != "ACTIVE":
    print("Processing video...")
    print("File state:", your_file.state)
    time.sleep(5)
    your_file = client.files.get(name=your_file.name)

print(
    client.models.count_tokens(
        model="gemini-2.0-flash", contents=[prompt, your_file]
    )
)
# ( e.g., total_tokens: 300 )

response = client.models.generate_content(
    model="gemini-2.0-flash", contents=[prompt, your_file]
)
print(response.usage_metadata)
# ( e.g., prompt_token_count: 301, candidates_token_count: 60, total_token_count: 361 )
count_tokens.py