The /public/models endpoint provides a list of all available AI models for chat completions and other generative tasks. Use this endpoint to discover model IDs, capabilities, pricing, and other metadata before making requests to the Lunos API.
GET /public/modelsNo authentication is required to access this endpoint.
The response is a JSON array of model objects. Each object contains details about a model, including its ID, name, provider, capabilities, pricing, and status.
1[
2 {
3 "id": "openai/gpt-4o",
4 "name": "GPT-4o",
5 "parameters": {
6 "context": 128000,
7 "max_output_tokens": 4096,
8 "size": "4B"
9 },
10 "provider": "openai",
11 "pricePerMillionTokens": {
12 "input": 5.0,
13 "output": 15.0
14 },
15 "capabilities": ["text-generation", "chat", "vision"],
16 "status": "available"
17 }
18]| Field | Type | Description |
|---|---|---|
id | string | Unique model identifier (use this in API requests). |
name | string | Human-readable model name. |
parameters.context | number | Maximum context window (tokens). |
parameters.max_output_tokens | number | Maximum output tokens per request. |
parameters.size | string | Model size (e.g., "4B"). |
provider | string | Model provider (e.g., "openai"). |
pricePerMillionTokens.input | number | Cost per 1M input tokens (USD). |
pricePerMillionTokens.output | number | Cost per 1M output tokens (USD). |
capabilities | string[] | Array of supported features (e.g., text-generation, chat, vision). |
status | string | Model availability status (e.g., available). |
curl -X GET https://api.lunos.tech/public/models1[
2 {
3 "id": "openai/gpt-4o",
4 "name": "GPT-4o",
5 "parameters": {
6 "context": 128000,
7 "max_output_tokens": 4096,
8 "size": "4B"
9 },
10 "provider": "openai",
11 "pricePerMillionTokens": {
12 "input": 5.0,
13 "output": 15.0
14 },
15 "capabilities": ["text-generation", "chat", "vision"],
16 "status": "available"
17 },
18 {
19 "id": "openai/text-embedding-3-small",
20 "name": "Text Embedding 3 Small",
21 "parameters": {
22 "context": 8192,
23 "max_output_tokens": 2000,
24 "size": "1B"
25 },
26 "provider": "openai",
27 "pricePerMillionTokens": {
28 "input": 0.1,
29 "output": 0.3
30 },
31 "capabilities": ["embedding"],
32 "status": "available"
33 }
34]id field as the model parameter in your API requests.capabilities array to ensure the model supports your use case (e.g., chat, vision, embedding).status field to confirm the model is available before using it in production.pricePerMillionTokens to optimize for cost based on your expected usage.parameters for model-specific limits like context window and max output tokens.No headings found on this page.