Gaps found while pinning v1.20261013.6 in Grida FX #21

Grida FX now pins v1.20261013.6 when it is built (gridaco/fx#69, gridaco/fx#79): it keeps a projection of the schema-defined facts its built-in routes use and checks its routes against it. These facts were missing or outside the schema:

• no answer shapes for fal's endpoints (only grida bindings have result_schema_url);
• no card for Gemini Omni Flash;
• no endpoint facts on the OpenAI binding;
• no mask facts;
• GG's meters have no quantity per request;
• media prices sit outside the schema, and token_pricing cannot express image models;
• no ElevenLabs binding or US-dollar rate;
• input_references is typed as an integer on OpenRouter;
• no size on OpenRouter;
• image_constraints only on fal;
• no references (the number of input pictures) on 4 of the 17 OpenRouter image bindings;
• no output_format on OpenRouter;
• the rigging card's input.formats and a speech card's input.audio_tags are not schema-defined;
• no request parameters on the grida endpoints for images, video and 3D;
• Tripo's /generation/multiview-to-model is recorded with input image, where GG's multiview endpoint for the same model has multi_image.

Found while building the AI provider contract (plan, gridaco/fx#69, gridaco/fx#79).