Get Model by Name
Get detailed information about a specific model by its name, including pricing.
Path parameters
Headers
Response
Successful Response
Name of the model
Provider of the model (e.g., openai, anthropic)
Type of model: 'llm', 'embedding', or 'image'
Maximum context window size in tokens
Maximum number of output tokens
Whether the model supports tool/function calling
Whether the model accepts image input
Whether the model accepts audio input
Whether the model accepts video input
Whether the model can generate images
Whether the model can generate audio/speech
Whether the model can generate video
Whether the model is marked as reasoning/thinking capable
Whether the catalog marks this model as supporting JSON object / structured text responses (null if unknown)
API mode/routing hint (e.g., chat_completions, responses, completions)
Embedding dimensions (for embedding models)
Text input cost per 1M tokens (USD)
Cached text input cost per 1M tokens (USD)
Cache-write text input cost per 1M tokens (USD)
Image input cost per 1M tokens (USD)
Text output cost per 1M tokens (USD)
Image output cost per 1M tokens (USD)
Flat cost per generated image (USD), for dall-e style models
Token threshold after which tier-2 pricing applies
Tier-2 input cost per 1 million tokens
Tier-2 cached input cost per 1 million tokens
Tier-2 cache-write input cost per 1 million tokens
Tier-2 output cost per 1 million tokens
Last time the model was updated
Changes
No recorded changes to this endpoint across all 1 revision of this API.