Best practices to handle prompts that are too long for the LLM API (eg., Anthropic, OpenAi)?

Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'prompt is too long: 200936 tokens > 199999 maximum'}}

from anthropic_bedrock import AnthropicBedrock
import anthropic
import random
import string

# Function to generate a random word
def generate_random_word(length):
    return ''.join(random.choices(string.ascii_lowercase, k=length))

# Generate ~150K words
words = [generate_random_word(random.randint(3, 10)) for _ in range(150000)]
print(f'Number of words: {len(words)}')

test_prompt = ' '.join(words)

# Function to count the number of tokens
def count_number_tokens(prompt: str, verbose: bool = False) -> tuple[int, int]:
    bedrock_client = AnthropicBedrock()
    anthropic_client = anthropic.Client()

    try:
        token_count_bedrock = bedrock_client.count_tokens(prompt)
    except Exception as e:
        token_count_bedrock = -1
        if verbose:
            print(f"Error counting tokens with Bedrock: {e}")

    try:
        token_count_anthropic = anthropic_client.count_tokens(prompt)
    except Exception as e:
        token_count_anthropic = -1
        if verbose:
            print(f"Error counting tokens with Anthropic: {e}")

    if verbose:
        print(f'token_count_bedrock={token_count_bedrock}, token_count_anthropic={token_count_anthropic}')
    return token_count_bedrock, token_count_anthropic

# Maximum token limit
max_tokens = 199_999

# Function to trim the prompt
def trim_prompt(prompt: str, max_tokens: int) -> str:
    initial_length = len(prompt)
    while True:
        _, token_count = count_number_tokens(prompt)
        if token_count <= max_tokens:
            break
        # Reduce the size of the prompt
        prompt = prompt[:len(prompt) - 1000]
        if len(prompt) == initial_length:
            # Avoid infinite loop in case prompt length doesn't change
            prompt = prompt[:len(prompt) // 2]
    return prompt

# Trim the prompt to fit within the token limit
trimmed_prompt = trim_prompt(test_prompt, max_tokens)

# Final check
final_token_count_bedrock, final_token_count_anthropic = count_number_tokens(trimmed_prompt, verbose=True)
print(f'Final prompt length: {len(trimmed_prompt)} characters')
print(f'Final token count (Bedrock): {final_token_count_bedrock}')
print(f'Final token count (Anthropic): {final_token_count_anthropic}')