Llm Models Foundation Models Create

POST

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

POST

/llm_models/foundation_models/

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

201Created

1 {
2   "id": 1,
3   "model_name": "string",
4   "updated_at": "2024-01-15T09:30:00Z",
5   "display_name": "string",
6   "speed": 1.1,
7   "max_context_window": 1,
8   "model_size": 1,
9   "mmlu_score": 1.1,
10   "mt_bench_score": 1.1,
11   "big_bench_score": 1.1,
12   "input_cost": 1.1,
13   "output_cost": 1.1,
14   "rate_limit": 1,
15   "token_rate_limit": 1,
16   "multilingual": 1,
17   "streaming_support": 1,
18   "function_call": 1,
19   "enforce_function_call": 1,
20   "weight": 1.1,
21   "image_support": 1,
22   "hf_url": "string",
23   "model_description": "string",
24   "model_params": [
25     "string"
26   ],
27   "total_requests": 1,
28   "total_cost": 1.1,
29   "total_tokens": 1,
30   "total_completion_tokens": 1,
31   "total_prompt_tokens": 1,
32   "avg_tps": 1.1
33 }

Authentication

AuthorizationBearer

JWT access token or Respan API key

Request

This endpoint expects an object.

model_namestringRequired1-255 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

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

hf_urlstringOptionalformat: "uri"<=200 characters

model_descriptionstringOptional

model_paramslist of stringsOptional

total_requestsintegerOptional-2147483648-2147483647

total_costdoubleOptional

total_tokenslongOptional-9223372036854776000-9223372036854776000

total_completion_tokenslongOptional-9223372036854776000-9223372036854776000

total_prompt_tokenslongOptional-9223372036854776000-9223372036854776000

avg_tpsdoubleOptional

Response

idintegerRead-only

model_namestring<=255 characters

updated_atdatetimeRead-only

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

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

hf_urlstringformat: "uri"<=200 characters

model_descriptionstring

model_paramslist of strings

total_requestsinteger-2147483648-2147483647

total_costdouble

total_tokenslong-9223372036854776000-9223372036854776000

total_completion_tokenslong-9223372036854776000-9223372036854776000

total_prompt_tokenslong-9223372036854776000-9223372036854776000

avg_tpsdouble