Proposed multi-provider capabilities and pricing API. Blog post: https://paolino.me/standard-api-llm-capabilities-pricing/

model.yml

# This is a YAML file so I can have comments but the API should obviously return an array of models in JSON.
# Legend:
#  Required: this is important to have in v1.
#  Optional: this is still important but can wait for v2.

id: gpt-4.5-preview                     # Required, will match it with the OpenAI API
name: GPT-4.5 Preview                   # Required
provider: openai                        # Required
family: gpt45                           # Optional, each model page is a family for OpenAI models
context_window: 128000                  # Required
max_output_tokens: 16384                # Required
knowledge_cutoff: 20231001              # Optional

modalities:
  input: # Sort arrays alphabetically to make diffs consistent
    - text
    - image
    - audio
    - pdf
  output:
    - text
    - image
    - audio
    - embeddings
    - moderation

capabilities:
  - streaming           # Optional
  - function_calling    # Required
  - structured_output   # Required
  - predicted_outputs   # Optional
  - distillation        # Optional
  - fine_tuning         # Optional
  - batch               # Required
  - realtime            # Optional
  - image_generation    # Required
  - speech_generation   # Required
  - transcription       # Required
  - translation         # Optional
  - citations           # Optional - from Anthropic
  - reasoning           # Optional - called Extended Thinking in Anthropic's lingo

pricing:
  text_tokens:
    standard:
      input_per_million: 75.0           # Required
      cached_input_per_million: 37.5    # Required
      output_per_million: 150.0         # Required
      reasoning_output_per_million: 0   # Optional
    batch:
      input_per_million: 37.5           # Required
      output_per_million: 75.0          # Required
  images:
    standard:
      input: 0.0                        # Optional
      output: 0.0                       # Optional
    batch:
      input: 0.0                        # Optional
      output: 0.0                       # Optional
  audio_tokens:
    standard:
      input_per_million: 0.0            # Optional
      output_per_million: 0.0           # Optional
    batch:
      input_per_million: 0.0            # Optional
      output_per_million: 0.0           # Optional
  embeddings:
    standard:
      input_per_million: 0.0            # Required
    batch:
      input_per_million: 0.0            # Required

Thank you so much for the info @MadBomber!

Updated the spec taking inspiration from OpenRouter @raznem @MadBomber