wehub-resource-sync
43 lines
958 B
HTTP
43 lines
958 B
HTTP
###
|
|
# @name List model directly from llama-cpp provider
|
|
GET http://{{llama-address}}/v1/models
|
|
Authorization: Bearer {{LLAMACPP_API_KEY}}
|
|
|
|
###
|
|
# @name List all models
|
|
GET {{omniroute-address}}/models
|
|
Authorization: Bearer {{OMNIROUTE_API_KEY}}
|
|
Content-Type: application/json
|
|
|
|
###
|
|
# @name Send a standard OpenAI chat request directly to llama-cpp provider
|
|
POST http://{{llama-address}}/chat/completions
|
|
Authorization: Bearer {{LLAMACPP_API_KEY}}
|
|
|
|
{
|
|
"model": "unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ2_M",
|
|
"stream": true,
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Tell me a joke."
|
|
}
|
|
]
|
|
}
|
|
|
|
###
|
|
# @name Send a standard OpenAI chat request to this llama-cpp provider
|
|
POST {{omniroute-address}}/v1/chat/completions
|
|
Authorization: Bearer {{OMNIROUTE_API_KEY}}
|
|
|
|
{
|
|
"model": "llamacpp/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ2_M",
|
|
"stream": true,
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Tell me a joke."
|
|
}
|
|
]
|
|
}
|
|
### |