luv13 models
Definition
luv13 is an OpenAI-compatible API for open-weight models at base URL https://api.luv13.ai/v1, and GET https://api.luv13.ai/v1/models returns the exact model ids you pass in the model field. Every model costs one flat $0.33 per 1M tokens, with input priced the same as output.
Key takeaways
- luv13 serves 7 models today. Their ids are the strings returned by GET https://api.luv13.ai/v1/models, e.g. luv13/glm-5.3-flash.
- Pick a model by putting its id in the model field of a standard OpenAI-style POST /v1/chat/completions request.
- Every model costs a flat $0.33 per 1M tokens, input = output (current interim rate). For example, 800k in + 200k out = 1.0M tokens = $0.33.
- Each model has its own page under /docs/m/ with the maker's details.
List
List the models
No API key is needed to list the models.
curl https://api.luv13.ai/v1/modelsSample response (real, trimmed to 2 of 7 entries):
{
"object": "list",
"data": [
{"id": "luv13/deepseek-v4-pro", "object": "model", "created": 1700000000, "owned_by": "luv13"},
{"id": "luv13/deepseek-v4.1-flash", "object": "model", "created": 1700000000, "owned_by": "luv13"}
]
}The list above is the source of truth. If this page and /v1/models ever disagree, /v1/models is right.
Ids
Model ids
| Model | model id | Price (flat, input = output) |
|---|---|---|
| Kimi K3 | luv13/kimi-k3 | $0.33 / 1M tokens |
| Kimi K3 Fast | luv13/kimi-k3-fast | $0.33 / 1M tokens |
| GLM 5.3 | luv13/glm-5.3 | $0.33 / 1M tokens |
| GLM-5.3 Flash | luv13/glm-5.3-flash | $0.33 / 1M tokens |
| DeepSeek V4.1 Flash | luv13/deepseek-v4.1-flash | $0.33 / 1M tokens |
| DeepSeek V4-Pro (temporarily unavailable) | luv13/deepseek-v4-pro | $0.33 / 1M tokens |
| Qwen 3.8 27B | luv13/qwen-3.8-27b | $0.33 / 1M tokens |
Browse every model and its price at models.luv13.ai.
Choose
How to choose a model
Put any id from the table in the model field. Everything else is a standard OpenAI chat completion. To switch models, change only that string.
curl https://api.luv13.ai/v1/chat/completions \
-H "Authorization: Bearer $LUV13_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "luv13/glm-5.3-flash",
"messages": [
{"role": "user", "content": "ping"}
]
}'For getting a key, see the Quickstart. For billing, see Pricing.
Cost
What it costs
800k input tokens + 200k output tokens = 1.0M tokens × $0.33 = $0.33. The rate is the same on every model and for input and output.