curl --request GET \
--url https://api.intelligence.io.solutions/api/v1/embedding-models \
--header 'Authorization: Bearer <token>'{
"object": "list",
"data": [
{
"id": "<string>",
"object": "model",
"created": 123,
"owned_by": "io-intelligence",
"root": "<string>",
"parent": "<string>",
"max_model_len": 123,
"permission": [
{
"id": "<string>",
"object": "model_permission",
"created": 123,
"allow_create_engine": false,
"allow_sampling": true,
"allow_logprobs": true,
"allow_search_indices": false,
"allow_view": true,
"allow_fine_tuning": false,
"organization": "*",
"group": "<string>",
"is_blocking": false
}
],
"max_tokens": 123,
"context_window": 123,
"supports_images_input": true,
"supports_prompt_cache": true,
"input_token_price": 123,
"output_token_price": 123,
"cache_write_token_price": 123,
"cache_read_token_price": 123,
"precision": "<string>"
}
]
}Retrieves a list of available models for the Embeddings API.
curl --request GET \
--url https://api.intelligence.io.solutions/api/v1/embedding-models \
--header 'Authorization: Bearer <token>'{
"object": "list",
"data": [
{
"id": "<string>",
"object": "model",
"created": 123,
"owned_by": "io-intelligence",
"root": "<string>",
"parent": "<string>",
"max_model_len": 123,
"permission": [
{
"id": "<string>",
"object": "model_permission",
"created": 123,
"allow_create_engine": false,
"allow_sampling": true,
"allow_logprobs": true,
"allow_search_indices": false,
"allow_view": true,
"allow_fine_tuning": false,
"organization": "*",
"group": "<string>",
"is_blocking": false
}
],
"max_tokens": 123,
"context_window": 123,
"supports_images_input": true,
"supports_prompt_cache": true,
"input_token_price": 123,
"output_token_price": 123,
"cache_write_token_price": 123,
"cache_read_token_price": 123,
"precision": "<string>"
}
]
}The access token received from the authorization server in the OAuth 2.0 flow.
JWT token
io.net provided API Key
API key set by an SDK client
Successful Response
Show child attributes
Show child attributes
Maximum number of tokens that can be generated in a single response
Maximum number of tokens that can be processed in the model's context window
Whether the model supports image inputs for multimodal processing
Whether the model supports prompt caching to improve performance
Price per token for input processing (in dollars)
Price per token for output generation (in dollars)
Price per token for writing to prompt cache (in dollars)
Price per token for reading from prompt cache (in dollars)
Model precision type (e.g., 'fp16', 'fp32', 'int8', 'int4')
Was this page helpful?