Models
List available models and their capabilities.
GET /v1/models
Returns every model your key can route to, with context limits, pricing, and capability flags.
Request
GET/v1/models
curl https://api.basemnt.ai/v1/models \
-H "Authorization: Bearer $SK_KEY"Response
200-response.json
{
"object": "list",
"data": [
{
"id": "z-ai/glm-5.2",
"object": "model",
"created": 1759000000,
"owned_by": "basemnt",
"context_length": 1048576,
"max_output_tokens": 131072,
"streaming": true,
"tools": true,
"vision": false,
"input_price_per_m": 0.9744,
"output_price_per_m": 3.0624
}
]
}Catalog
| Model ID | Context | Max output | Tools | Vision |
|---|---|---|---|---|
z-ai/glm-5.2 | 1,048,576 | 131,072 | ✓ | — |
deepseek/deepseek-v4-flash-0731 | 1,048,576 | 65,536 | ✓ | — |
minimax/minimax-m3 | 1,048,576 | 512,000 | ✓ | ✓ |
Token prices are upstream costs
Plans are metered per request, not per token — token pricing shown by
GET /v1/models reflects upstream provider cost and never appears on your bill.
Model IDs are passed verbatim to the model field of
Chat Completions and
Messages. Unknown IDs return a 400 listing the valid models.