fix(llm): check multi modal input with provider and fix cost calculation

[fffonion]

Summary

For multi modal inputs (openai or bedrock), the input format is changed from:

messages=[
    {
      "role": "user",
      "content": "What's an apple?
    }
]

to

messages=[
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What's in this image?"},
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
          },
        },
      ],
    }
]

Checklist

• The Pull Request has tests
• A changelog file has been created under changelog/unreleased/kong or skip-changelog label added on PR if changelog is unnecessary. README.md
• There is a user-facing docs PR against https://github.com/Kong/docs.konghq.com - PUT DOCS PR HERE

Issue reference

AG-61

[fffonion]

needs tests

[StarlightIbuki]

Not a blocker. Are we going to keep compatible to the old format?

[fffonion]

both formats are not deprecated, but right not only openai and bedrock supports the multi-modal format as well as the non multi-modal formats ("old format")

[team-gateway-bot]

Successfully created cherry-pick PR for master:

• https://github.com/kong/kong-ee/pull/9989