LLM API
List Models
Model APIs
- Introduction
- LLM API
- Image, Audio and Video
GPUs
- GPU Instance
LLM API
List Models
GET
/
v3
/
openai
/
models
curl --request GET \
--url https://api.novita.ai/v3/openai/models \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>'
{
"data": [
{
"created": 1733560109,
"id": "meta-llama/llama-3.3-70b-instruct",
"object": "model",
"input_token_price_per_m": 3900,
"output_token_price_per_m": 3900,
"title": "meta-llama/llama-3.3-70b-instruct",
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.",
"context_size": 131072
},
// more models here...
]
}
Lists the currently available models for the LLM API, and provides basic information about each one. This endpoint is compatible with OpenAI API.
Request Headers
Enum: application/json
Bearer authentication format, for example: Bearer {{API Key}}.
Response
{
"data": [
{
"created": 1733560109,
"id": "meta-llama/llama-3.3-70b-instruct",
"object": "model",
"input_token_price_per_m": 3900,
"output_token_price_per_m": 3900,
"title": "meta-llama/llama-3.3-70b-instruct",
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.",
"context_size": 131072
},
// more models here...
]
}
Array of model objects with the following properties:
The model identifier, which can be referenced in the API endpoints.
The Unix timestamp (in seconds) when the model was created.
The object type, which is always “model”.
The price per million input tokens.
The price per million output tokens.
The title of the model.
The description of the model.
The maximum context size of the model.
Was this page helpful?
curl --request GET \
--url https://api.novita.ai/v3/openai/models \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>'
{
"data": [
{
"created": 1733560109,
"id": "meta-llama/llama-3.3-70b-instruct",
"object": "model",
"input_token_price_per_m": 3900,
"output_token_price_per_m": 3900,
"title": "meta-llama/llama-3.3-70b-instruct",
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\n\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.",
"context_size": 131072
},
// more models here...
]
}