Llm Models Model Create

POST

https://api.respan.ai/llm_models/model/:id/

POST

/llm_models/model/:id/

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

200Successful

1 {
2   "id": 1,
3   "provider": {
4     "id": 1,
5     "provider_name": "string",
6     "provider_id": "string",
7     "created_at": "2024-01-15T09:30:00Z",
8     "updated_at": "2024-01-15T09:30:00Z",
9     "project": "string",
10     "litellm_provider_id": "string",
11     "moderation": "string",
12     "is_managed": true,
13     "respan_discount_rate": 1.1
14   },
15   "supported_params": "string",
16   "model_name": "string",
17   "is_byok": true,
18   "effective_discount_rate": 1.1,
19   "project": "string",
20   "affiliation_category": "custom",
21   "is_managed": true,
22   "is_called_by_custom_name": true,
23   "base_model_name": "string",
24   "display_name": "string",
25   "speed": 1.1,
26   "max_context_window": 1,
27   "model_size": 1,
28   "mmlu_score": 1.1,
29   "mt_bench_score": 1.1,
30   "big_bench_score": 1.1,
31   "input_cost": 1.1,
32   "output_cost": 1.1,
33   "cache_hit_input_cost": 1.1,
34   "cache_creation_input_cost": 1.1,
35   "respan_discount_rate": 1.1,
36   "rate_limit": 1,
37   "token_rate_limit": 1,
38   "multilingual": 1,
39   "streaming_support": 1,
40   "function_call": 1,
41   "enforce_function_call": 1,
42   "weight": 1.1,
43   "image_support": 1,
44   "order": 1,
45   "sdk": "string",
46   "foundation_model_name": "string",
47   "drop_params": [
48     "string"
49   ],
50   "overridden_fields": [
51     "string"
52   ],
53   "deprecated": true,
54   "status": "active",
55   "is_verified": true,
56   "total_requests": 1,
57   "total_cost": 1.1,
58   "total_tokens": 1,
59   "total_completion_tokens": 1,
60   "total_prompt_tokens": 1,
61   "avg_tps": 1.1,
62   "source": "hardcoded",
63   "model_type": "chat",
64   "metadata": {
65     "privacy_policy_url": "string",
66     "zero_data_retention": true,
67     "prompt_training": true,
68     "prompt_logging": true,
69     "moderation": true,
70     "is_available_on_credits": true,
71     "stream_cancellation_supported": true,
72     "precision": "string",
73     "quantization": "string",
74     "release_date": "string",
75     "context_size": 1,
76     "weekly_tokens": 1,
77     "daily_tokens": 1,
78     "benchmarks": {
79       "deepswe": {
80         "version": "string",
81         "generated_at": "string",
82         "n_tasks_in_set": 1,
83         "model": "string",
84         "harness": "string",
85         "reasoning_effort": "string",
86         "config": "string",
87         "source": "string",
88         "pass_rate": 0.5,
89         "pass_at_1": 0.5,
90         "pass_at_4": 0.5
91       }
92     }
93   },
94   "foundation_model": 1
95 }

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

Path parameters

idintegerRequired

Request

This endpoint expects an object.

providerobjectRequired

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

speeddoubleOptional

max_context_windowintegerOptional-2147483648-2147483647

model_sizeintegerOptional-2147483648-2147483647

mmlu_scoredoubleOptional

mt_bench_scoredoubleOptional

big_bench_scoredoubleOptional

input_costdoubleOptional

output_costdoubleOptional

cache_hit_input_costdoubleOptional

cache_creation_input_costdoubleOptional

respan_discount_ratedouble or nullOptional

rate_limitintegerOptional-2147483648-2147483647

token_rate_limitintegerOptional-2147483648-2147483647

multilingualintegerOptional-2147483648-2147483647

streaming_supportintegerOptional-2147483648-2147483647

function_callintegerOptional-2147483648-2147483647

enforce_function_callintegerOptional-2147483648-2147483647

weightdoubleOptional

image_supportintegerOptional-2147483648-2147483647

orderintegerOptional-2147483648-2147483647

sdkstringOptional1-255 characters

foundation_model_namestringOptional<=255 characters

drop_paramslist of stringsOptional

overridden_fieldslist of stringsOptional

load_balance_backupsanyOptional

fallbacksanyOptional

deprecatedbooleanOptional

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.

total_requestslongOptional-9223372036854776000-9223372036854776000

total_costdoubleOptional

total_tokenslongOptional-9223372036854776000-9223372036854776000

total_completion_tokenslongOptional-9223372036854776000-9223372036854776000

total_prompt_tokenslongOptional-9223372036854776000-9223372036854776000

avg_tpsdoubleOptional

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.

foundation_modelinteger or nullOptional

Response

idintegerRead-only

providerobject

supported_paramsstringRead-only

model_namestring<=255 characters

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

speeddouble

max_context_windowinteger-2147483648-2147483647

model_sizeinteger-2147483648-2147483647

mmlu_scoredouble

mt_bench_scoredouble

big_bench_scoredouble

input_costdouble

output_costdouble

cache_hit_input_costdouble

cache_creation_input_costdouble

respan_discount_ratedouble or null

rate_limitinteger-2147483648-2147483647

token_rate_limitinteger-2147483648-2147483647

multilingualinteger-2147483648-2147483647

streaming_supportinteger-2147483648-2147483647

function_callinteger-2147483648-2147483647

enforce_function_callinteger-2147483648-2147483647

weightdouble

image_supportinteger-2147483648-2147483647

orderinteger-2147483648-2147483647

sdkstring<=255 characters

foundation_model_namestring<=255 characters

drop_paramslist of strings

overridden_fieldslist of strings

load_balance_backupsany

fallbacksany

deprecatedboolean

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.

total_requestslong-9223372036854776000-9223372036854776000

total_costdouble

total_tokenslong-9223372036854776000-9223372036854776000

total_completion_tokenslong-9223372036854776000-9223372036854776000

total_prompt_tokenslong-9223372036854776000-9223372036854776000

avg_tpsdouble

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.

foundation_modelinteger or null