Llm Models Models Create

POST

https://api.respan.ai/llm_models/models/

POST

/llm_models/models/

$ curl -X POST https://api.respan.ai/llm_models/models/ \
>      -H "Authorization: Bearer <token>" \
>      -H "Content-Type: application/json" \
>      -d '{
>   "model_name": "string",
>   "organization": 1
> }'

201Created

1 {
2   "provider": {
3     "provider_name": "string",
4     "provider_id": "string",
5     "created_at": "2024-01-15T09:30:00Z",
6     "updated_at": "2024-01-15T09:30:00Z",
7     "id": "string",
8     "project": "string",
9     "respan_discount_rate": 1.1
10   },
11   "supported_params": "string",
12   "model_name": "string",
13   "id": "string",
14   "is_byok": true,
15   "effective_discount_rate": 1.1,
16   "project": "string",
17   "affiliation_category": "custom",
18   "is_managed": true,
19   "is_called_by_custom_name": true,
20   "base_model_name": "string",
21   "display_name": "string",
22   "max_context_window": 1,
23   "input_cost": 1.1,
24   "output_cost": 1.1,
25   "cache_hit_input_cost": 1.1,
26   "cache_creation_input_cost": 1.1,
27   "respan_discount_rate": 1.1,
28   "streaming_support": 1,
29   "function_call": 1,
30   "image_support": 1,
31   "overridden_fields": [
32     "string"
33   ],
34   "status": "active",
35   "is_verified": true,
36   "source": "hardcoded",
37   "model_type": "chat",
38   "metadata": {
39     "privacy_policy_url": "string",
40     "zero_data_retention": true,
41     "prompt_training": true,
42     "prompt_logging": true,
43     "moderation": true,
44     "is_available_on_credits": true,
45     "stream_cancellation_supported": true,
46     "precision": "string",
47     "quantization": "string",
48     "release_date": "string",
49     "context_size": 1,
50     "weekly_tokens": 1,
51     "daily_tokens": 1,
52     "benchmarks": {
53       "deepswe": {
54         "version": "string",
55         "generated_at": "string",
56         "n_tasks_in_set": 1,
57         "model": "string",
58         "harness": "string",
59         "reasoning_effort": "string",
60         "config": "string",
61         "source": "string",
62         "pass_rate": 0.5,
63         "pass_at_1": 0.5,
64         "pass_at_4": 0.5
65       }
66     }
67   }
68 }

POST handler with superadmin-only field protection.

Strips superadmin-only fields from non-superadmin requests before delegating to OrganizationInjectionMixin.post() for org injection.

Authentication

AuthorizationBearer

JWT access token or Respan API key

Request

This endpoint expects an object.

model_namestringRequired1-255 characters

organizationinteger or nullRequired

projectstring or nullOptional>=1 character

affiliation_categoryenumOptional

custom - Custom
keywordsai - Keywordsai

is_managedbooleanOptional

is_called_by_custom_namebooleanOptional

base_model_namestringOptional<=255 characters

display_namestringOptional<=255 characters

max_context_windowintegerOptional-2147483648-2147483647

input_costdoubleOptional

output_costdoubleOptional

cache_hit_input_costdoubleOptional

cache_creation_input_costdoubleOptional

respan_discount_ratedouble or nullOptional

streaming_supportintegerOptional-2147483648-2147483647

function_callintegerOptional-2147483648-2147483647

image_supportintegerOptional-2147483648-2147483647

overridden_fieldslist of stringsOptional

load_balance_backupsanyOptional

statusenumOptional

active - Active
deprecated - Deprecated

is_verifiedbooleanOptional

Whether the model’s pricing has been human-verified. Unverified auto-discovered models are kept out of the live model dictionary.

sourceenumOptional

Source of truth for this model definition

hardcoded - Synced from Code
db - Database Only

model_typeenumOptional

Type of model: chat, embedding, or audio

chat - Chat
embedding - Embedding
audio - Audio

metadataobjectOptional

Flexible catalog metadata; known keys are documented, extras allowed.

Response

providerobject

Public API serializer for nested provider in model responses - hides internal fields

supported_paramsstringRead-only

model_namestring<=255 characters

idstringRead-only

is_byokbooleanRead-only

effective_discount_ratedoubleRead-only

projectstring or null

affiliation_categoryenum

custom - Custom
keywordsai - Keywordsai

is_managedboolean

is_called_by_custom_nameboolean

base_model_namestring<=255 characters

display_namestring<=255 characters

max_context_windowinteger-2147483648-2147483647

input_costdouble

output_costdouble

cache_hit_input_costdouble

cache_creation_input_costdouble

respan_discount_ratedouble or null

streaming_supportinteger-2147483648-2147483647

function_callinteger-2147483648-2147483647

image_supportinteger-2147483648-2147483647

overridden_fieldslist of strings

load_balance_backupsany

statusenum

active - Active
deprecated - Deprecated

is_verifiedboolean

Whether the model’s pricing has been human-verified. Unverified auto-discovered models are kept out of the live model dictionary.

sourceenum

Source of truth for this model definition

hardcoded - Synced from Code
db - Database Only

model_typeenum

Type of model: chat, embedding, or audio

chat - Chat
embedding - Embedding
audio - Audio

metadataobject

Flexible catalog metadata; known keys are documented, extras allowed.