total_prompt_tokens += _parsed_response["inputTextTokenCount"]  # always 0 for image inputs

# image_count IS correctly counted (fix from #21646):
if image_count > 0:
    prompt_tokens_details = PromptTokensDetailsWrapper(image_count=image_count)

# But prompt_tokens is set from total_prompt_tokens, which is still 0:
usage = Usage(
    prompt_tokens=total_prompt_tokens,   # <- 0 for image-only input
    total_tokens=total_prompt_tokens,    # <- 0
    prompt_tokens_details=prompt_tokens_details,
)

---

"amazon.titan-embed-image-v1": {
    "input_cost_per_image": 6e-05,
    "input_cost_per_token": 8e-07
}

---

prompt_tokens_details = None
if image_count > 0:
    prompt_tokens_details = PromptTokensDetailsWrapper(
        image_count=image_count,
        image_tokens=image_count,  # populate the existing but currently unused field
    )

usage = Usage(
    prompt_tokens=total_prompt_tokens + image_count,   # non-zero when images were processed
    completion_tokens=0,
    total_tokens=total_prompt_tokens + image_count,
    prompt_tokens_details=prompt_tokens_details,
)

---

import base64
from io import BytesIO
from PIL import Image
from litellm import embedding

# Image must be a data URI — litellm's is_base64_encoded() requires `data:` prefix
img = Image.new("RGB", (8, 8), color="blue")
buf = BytesIO()
img.save(buf, format="PNG")
img_b64 = base64.b64encode(buf.getvalue()).decode("utf-8")
img_data_uri = f"data:image/png;base64,{img_b64}"

response = embedding(
    model="amazon.titan-embed-image-v1",
    input=[img_data_uri],
    aws_region_name="us-east-1",
)

print(response.usage)
# Usage(prompt_tokens=0, total_tokens=0, ...)  ← BUG: should be non-zero

print(response.usage.prompt_tokens_details)
# PromptTokensDetailsWrapper(image_count=1)  ← image IS tracked here, just not surfaced in prompt_tokens

---

import json, base64, boto3
from io import BytesIO
from PIL import Image

img = Image.new("RGB", (8, 8), color="blue")
buf = BytesIO()
img.save(buf, format="PNG")
img_b64 = base64.b64encode(buf.getvalue()).decode("utf-8")

bedrock = boto3.client("bedrock-runtime", region_name="us-east-1")
resp = bedrock.invoke_model(
    modelId="amazon.titan-embed-image-v1",
    body=json.dumps({"inputImage": img_b64}),
    accept="application/json",
    contentType="application/json",
)

print(json.loads(resp["body"].read()))
# {"embedding": [...], "inputTextTokenCount": 0}
# AWS intentionally returns inputTextTokenCount=0 for images —
# the model is priced PER IMAGE ($0.00006/image), not per token.
# There is no "inputImageTokenCount" field — AWS does not expose one.

---