File tree Expand file tree Collapse file tree 1 file changed +58
-0
lines changed
Expand file tree Collapse file tree 1 file changed +58
-0
lines changed Original file line number Diff line number Diff line change @@ -3019,9 +3019,36 @@ components:
30193019 example :
30203020 data :
30213021 - id : openai/gpt-4
3022+ canonical_slug : openai/gpt-4
30223023 name : GPT-4
30233024 created : 1692901234
30243025 description : GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.
3026+ pricing :
3027+ prompt : ' 0.00003'
3028+ completion : ' 0.00006'
3029+ request : ' 0'
3030+ image : ' 0'
3031+ context_length : 8192
3032+ architecture :
3033+ tokenizer : GPT
3034+ instruct_type : chatml
3035+ modality : text->text
3036+ input_modalities :
3037+ - text
3038+ output_modalities :
3039+ - text
3040+ top_provider :
3041+ context_length : 8192
3042+ max_completion_tokens : 4096
3043+ is_moderated : true
3044+ per_request_limits : null
3045+ supported_parameters :
3046+ - temperature
3047+ - top_p
3048+ - max_tokens
3049+ - frequency_penalty
3050+ - presence_penalty
3051+ default_parameters : null
30253052 ListEndpointsResponse :
30263053 type : object
30273054 description : List of available endpoints for a model
@@ -3030,6 +3057,37 @@ components:
30303057 name : GPT-4
30313058 created : 1692901234
30323059 description : GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.
3060+ architecture :
3061+ tokenizer : GPT
3062+ instruct_type : chatml
3063+ modality : text->text
3064+ input_modalities :
3065+ - text
3066+ output_modalities :
3067+ - text
3068+ endpoints :
3069+ - name : ' OpenAI: GPT-4'
3070+ model_name : GPT-4
3071+ context_length : 8192
3072+ pricing :
3073+ prompt : ' 0.00003'
3074+ completion : ' 0.00006'
3075+ request : ' 0'
3076+ image : ' 0'
3077+ provider_name : OpenAI
3078+ tag : openai
3079+ quantization : fp16
3080+ max_completion_tokens : 4096
3081+ max_prompt_tokens : 8192
3082+ supported_parameters :
3083+ - temperature
3084+ - top_p
3085+ - max_tokens
3086+ - frequency_penalty
3087+ - presence_penalty
3088+ status : default
3089+ uptime_last_30m : 99.5
3090+ supports_implicit_caching : true
30333091 PublicEndpoint :
30343092 type : object
30353093 description : Information about a specific model endpoint
You can’t perform that action at this time.
0 commit comments