Add context_over_200k for gemini-2.5-pro and adjust cache_read costs

[rovo89]

https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro
https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models-2.5 (rounds 0.125 to 0.13)

[rovo89]

@rekram1-node Thanks for merging! How long does it usually take for https://models.dev/api.json to reflect the changes? Currently, it doesn't even have the old cache_read cost, so my logic would price all input tokens at $1.25/M:

"gemini-2.5-pro": {
  "id": "gemini-2.5-pro",
  "name": "gemini-2.5-pro",
  "family": "gemini-pro",
  "attachment": true,
  "reasoning": false,
  "tool_call": true,
  "temperature": true,
  "knowledge": "2025-01",
  "release_date": "2025-06-17",
  "last_updated": "2025-06-17",
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "open_weights": false,
  "cost": {
    "input": 1.25,
    "output": 10
  },
  "limit": {
    "context": 1000000,
    "output": 65536
  }
},

EDIT: Sorry, I take that back. Just searched for "gemini-2.5-pro" and didn't notice it was for one of the many "resellers". The entry under "google" is correct.