Endpoints API Documentation
Endpoints (Models) APIs
Get Defaults
curl --request GET \
--url https://api.enkryptai.com/models/get-defaults \
--header 'apikey: <api-key>'{
"available_providers": [
"openai",
"together",
"huggingface",
"groq",
"azure_openai",
"anthropic",
"cohere",
"bedrock",
"gemini",
"ai21",
"fireworks",
"alibaba",
"portkey",
"deepseek",
"mistral",
"llama",
"openai_compatible",
"cohere_compatible",
"anthropic_compatible",
"custom"
],
"openai": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"SOC 2 Type 2",
"SOC 3",
"CSA STAR Level 1"
],
"model_config": {
"model_provider": "openai",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://openai.com",
"endpoint": {
"scheme": "https",
"host": "api.openai.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"together": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.together.ai",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.88,
"output_cost_1M_tokens": 0.88
},
"default_request_options": {
"temperature": 0.7,
"top_p": 0.7,
"top_k": 50
}
}
},
"huggingface": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "huggingface",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://huggingface.co",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/models/{model_name}/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"huggingface": {
"use_cache": false,
"wait_for_model": false
}
},
"default_request_options": {
"temperature": 0.7,
"top_p": null,
"top_k": null
}
}
},
"groq": {
"testing_for": "foundationModels",
"model_name": "llama3-8b-8192",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "groq",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://groq.com",
"endpoint": {
"scheme": "https",
"host": "api.groq.com",
"port": 443,
"base_path": "/openai/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.05,
"output_cost_1M_tokens": 0.08
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"azure_openai": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR"
],
"model_config": {
"model_provider": "azure_openai",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://microsoft.com",
"endpoint": {
"scheme": "https",
"host": "{azure_instance}.openai.azure.com",
"port": 443,
"base_path": "/openai/deployments/{azure_deployment_id}"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10,
"azure_instance": "instance_name",
"azure_api_version": "2024-10-21",
"azure_deployment_id": "gpt-4o"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"anthropic": {
"testing_for": "foundationModels",
"model_name": "claude-3-5-sonnet-latest",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2 Type 1",
"SOC 2 Type 2",
"HIPAA"
],
"model_config": {
"model_provider": "anthropic",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://anthropic.com",
"endpoint": {
"scheme": "https",
"host": "api.anthropic.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/complete",
"chat": "/chat/messages"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 3.75,
"output_cost_1M_tokens": 15,
"anthropic_version": "2023-06-01"
},
"default_request_options": {
"temperature": 1,
"top_p": null,
"top_k": null
}
}
},
"cohere": {
"testing_for": "foundationModels",
"model_name": "command",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"SOC 2 Type 2"
],
"model_config": {
"model_provider": "cohere",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://cohere.com",
"endpoint": {
"scheme": "https",
"host": "api.cohere.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/generate",
"chat": "/chat"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 0.3,
"top_p": 0.75,
"top_k": 0
}
}
},
"bedrock": {
"testing_for": "foundationModels",
"model_name": "amazon.titan-text-express-v1",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"ISO",
"CSA",
"FedRAMP",
"HIPAA",
"SOC 1 Type 2",
"SOC 3 Type 2",
"SOC 3 Type 2"
],
"model_config": {
"model_provider": "bedrock",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://aws.amazon.com/bedrock",
"endpoint": {
"scheme": "https",
"host": "bedrock-runtime.{aws_region}.amazonaws.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/model/{model_name}/invoke",
"chat": "/model/{model_name}/converse"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.2,
"output_cost_1M_tokens": 0.6,
"bedrock": {
"aws_region": "us-east-1"
}
},
"default_request_options": {
"temperature": 0.7,
"top_p": 0.9,
"top_k": null
}
}
},
"gemini": {
"testing_for": "foundationModels",
"model_name": "gemini-1.5-flash-latest",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"HIPAA",
"SOC 1 Type 2",
"SOC 3 Type 2",
"SOC 3 Type 2",
"ISO/IEC 27001",
"ISO/IEC 27017",
"ISO/IEC 27018",
"ISO/IEC 27701"
],
"model_config": {
"model_provider": "gemini",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://ai.google.dev",
"endpoint": {
"scheme": "https",
"host": "generativelanguage.googleapis.com",
"port": 443,
"base_path": "/v1beta/models/{model_name}/llm/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat"
},
"auth_data": {
"param_name": "key"
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": null,
"top_p": 0.95,
"top_k": null
}
}
},
"ai21": {
"testing_for": "foundationModels",
"model_name": "jamba-mini",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"HIPAA",
"SOC 2 Type 2",
"ISO/IEC 27001",
"ISO/IEC 27017",
"ISO/IEC 27018",
"ISO 42001"
],
"model_config": {
"model_provider": "ai21",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.ai21.com/jamba/",
"endpoint": {
"scheme": "https",
"host": "api.ai21.com",
"port": 443,
"base_path": "/studio/v1"
},
"paths": {
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 0.4,
"top_p": 1,
"top_k": null
}
}
},
"fireworks": {
"testing_for": "foundationModels",
"model_name": "accounts/fireworks/models/llama-v3p1-8b-instruct",
"model_version": "v1",
"certifications": [
"HIPAA",
"SOC 2 Type 2"
],
"model_config": {
"model_provider": "fireworks",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://fireworks.ai/",
"endpoint": {
"scheme": "https",
"host": "api.fireworks.ai",
"port": 443,
"base_path": "/inference/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"alibaba": {
"testing_for": "foundationModels",
"model_name": "qwen-plus",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "alibaba",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.alibabacloud.com/help/en/model-studio",
"endpoint": {
"scheme": "https",
"host": "dashscope-intl.aliyuncs.com",
"port": 443,
"base_path": "/compatible-mode/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": null,
"top_p": null,
"top_k": null
}
}
},
"portkey": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR",
"HIPAA",
"SOC 2 Type 2",
"ISO 27001:2022"
],
"model_config": {
"model_provider": "portkey",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://portkey.ai/",
"endpoint": {
"scheme": "https",
"host": "api.portkey.ai",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"deepseek": {
"testing_for": "foundationModels",
"model_name": "deepseek-chat",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "deepseek",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.deepseek.com/",
"endpoint": {
"scheme": "https",
"host": "api.deepseek.com",
"port": 443,
"base_path": ""
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"mistral": {
"testing_for": "foundationModels",
"model_name": "mistral-large-latest",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "mistral",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://mistral.ai",
"endpoint": {
"scheme": "https",
"host": "api.mistral.ai",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2,
"output_cost_1M_tokens": 6,
"mistral_format": "openai"
},
"default_request_options": {
"temperature": null,
"top_p": 1,
"top_k": null
}
}
},
"llama": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-2-7b-chat-hf",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "llama",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://llama.com",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/models/{model_name}/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"llama2_format": "openai"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"custom": {
"testing_for": "agents",
"certifications": [],
"model_config": {
"model_provider": "custom",
"hosting_type": "External",
"model_source": "https://huggingface.co",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/agents/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"input_modalities": [
"text",
"image",
"audio"
],
"output_modalities": [
"text"
],
"tools": [
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
],
"custom_headers": [
{
"key": "test",
"value": "test"
}
],
"custom_payload": {
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "{prompt}"
}
]
},
"custom_response_content_type": "json",
"custom_response_format": ".choices[0].message.content",
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"llama2_format": "openai"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
}
}Authorizations
Response
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
Provider of the model which determines the request response format
openai, together, huggingface, groq, azure_openai, anthropic, cohere, bedrock, gemini, ai21, fireworks, alibaba, portkey, deepseek, mistral, llama, openai_compatible, cohere_compatible, anthropic_compatible, custom "together"
Scheme of the endpoint
"https"
Host of the endpoint
"api.together.xyz"
Port of the endpoint
443
Base path of the endpoint
"/v1"
Hosting type of the model
External, Internal "External"
Source of the model
"https://together.ai"
Array of tools available to the model
[
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
]
Types of input that the model can process
text, image, audio ["text"]
Types of output that the model can generate
text ["text"]
< 100 won't enable async. > 100 will enable async mode. > 200 we can run boosted async (all tests in parallel). Default 20.
20
System prompt
""
["TOGETHER_AI_API_KEY"]
Array of custom headers to be sent with requests
[
{
"key": "X-Custom-Header",
"value": "custom-value"
}
]
A flexible object that can contain any custom key-value pairs for the request payload. Only condition is to include {prompt} in the payload.
{
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{ "role": "user", "content": "{prompt}" }
]
}
Content type of the custom response. Currently only supports JSON.
json "json"
Optional response format path. Jq format for json type (e.g. '.choices[0].message.content')
".choices[0].message.content"
2048
2.5
10
If Azure, it's instance type
"enkrypt2024"
If Azure, it's API version
"2024-02-01"
If Azure, it's deployment ID
"gpt3"
If Anthropic, it's version
""
If Llama2, it's format
openai "openai"
If Mistral, it's format
openai, ollama "openai"
If running Gemini on Vertex, specify the regional API endpoint (hostname only)
""
If running Gemini on Vertex, specify the project ID
""
If running Gemini on Vertex, specify the location ID
""
Name of the saved model
"Test Model"
Custom identifier for the model
"v1"
Purpose of testing
foundationModels, chatbotsAndCopilots, agents "foundationModels"
Name of the model. Required for foundationModels
"mistralai/Mixtral-8x7B-Instruct-v0.1"
List of certifications
[
"GDPR",
"CCPA",
"HIPAA",
"SOC 2 Type II",
"SOC 3"
]
{
"testing_for": "foundationModels",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"certifications": [],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": ["text"],
"output_modalities": ["text"],
"model_source": "https://together.ai",
"rate_per_min": 20,
"system_prompt": "",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"apikeys": ["xxxxx"],
"metadata": {},
"default_request_options": {}
},
"model_saved_name": "Test Model",
"model_version": "v1"
}
curl --request GET \
--url https://api.enkryptai.com/models/get-defaults \
--header 'apikey: <api-key>'{
"available_providers": [
"openai",
"together",
"huggingface",
"groq",
"azure_openai",
"anthropic",
"cohere",
"bedrock",
"gemini",
"ai21",
"fireworks",
"alibaba",
"portkey",
"deepseek",
"mistral",
"llama",
"openai_compatible",
"cohere_compatible",
"anthropic_compatible",
"custom"
],
"openai": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"SOC 2 Type 2",
"SOC 3",
"CSA STAR Level 1"
],
"model_config": {
"model_provider": "openai",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://openai.com",
"endpoint": {
"scheme": "https",
"host": "api.openai.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"together": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "together",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.together.ai",
"endpoint": {
"scheme": "https",
"host": "api.together.xyz",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.88,
"output_cost_1M_tokens": 0.88
},
"default_request_options": {
"temperature": 0.7,
"top_p": 0.7,
"top_k": 50
}
}
},
"huggingface": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "huggingface",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://huggingface.co",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/models/{model_name}/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"huggingface": {
"use_cache": false,
"wait_for_model": false
}
},
"default_request_options": {
"temperature": 0.7,
"top_p": null,
"top_k": null
}
}
},
"groq": {
"testing_for": "foundationModels",
"model_name": "llama3-8b-8192",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2"
],
"model_config": {
"model_provider": "groq",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://groq.com",
"endpoint": {
"scheme": "https",
"host": "api.groq.com",
"port": 443,
"base_path": "/openai/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.05,
"output_cost_1M_tokens": 0.08
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"azure_openai": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR"
],
"model_config": {
"model_provider": "azure_openai",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://microsoft.com",
"endpoint": {
"scheme": "https",
"host": "{azure_instance}.openai.azure.com",
"port": 443,
"base_path": "/openai/deployments/{azure_deployment_id}"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10,
"azure_instance": "instance_name",
"azure_api_version": "2024-10-21",
"azure_deployment_id": "gpt-4o"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"anthropic": {
"testing_for": "foundationModels",
"model_name": "claude-3-5-sonnet-latest",
"model_version": "v1",
"certifications": [
"GDPR",
"SOC 2 Type 1",
"SOC 2 Type 2",
"HIPAA"
],
"model_config": {
"model_provider": "anthropic",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://anthropic.com",
"endpoint": {
"scheme": "https",
"host": "api.anthropic.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/complete",
"chat": "/chat/messages"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 3.75,
"output_cost_1M_tokens": 15,
"anthropic_version": "2023-06-01"
},
"default_request_options": {
"temperature": 1,
"top_p": null,
"top_k": null
}
}
},
"cohere": {
"testing_for": "foundationModels",
"model_name": "command",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"SOC 2 Type 2"
],
"model_config": {
"model_provider": "cohere",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://cohere.com",
"endpoint": {
"scheme": "https",
"host": "api.cohere.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/generate",
"chat": "/chat"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 0.3,
"top_p": 0.75,
"top_k": 0
}
}
},
"bedrock": {
"testing_for": "foundationModels",
"model_name": "amazon.titan-text-express-v1",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"ISO",
"CSA",
"FedRAMP",
"HIPAA",
"SOC 1 Type 2",
"SOC 3 Type 2",
"SOC 3 Type 2"
],
"model_config": {
"model_provider": "bedrock",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://aws.amazon.com/bedrock",
"endpoint": {
"scheme": "https",
"host": "bedrock-runtime.{aws_region}.amazonaws.com",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/model/{model_name}/invoke",
"chat": "/model/{model_name}/converse"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 0.2,
"output_cost_1M_tokens": 0.6,
"bedrock": {
"aws_region": "us-east-1"
}
},
"default_request_options": {
"temperature": 0.7,
"top_p": 0.9,
"top_k": null
}
}
},
"gemini": {
"testing_for": "foundationModels",
"model_name": "gemini-1.5-flash-latest",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"HIPAA",
"SOC 1 Type 2",
"SOC 3 Type 2",
"SOC 3 Type 2",
"ISO/IEC 27001",
"ISO/IEC 27017",
"ISO/IEC 27018",
"ISO/IEC 27701"
],
"model_config": {
"model_provider": "gemini",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://ai.google.dev",
"endpoint": {
"scheme": "https",
"host": "generativelanguage.googleapis.com",
"port": 443,
"base_path": "/v1beta/models/{model_name}/llm/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat"
},
"auth_data": {
"param_name": "key"
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": null,
"top_p": 0.95,
"top_k": null
}
}
},
"ai21": {
"testing_for": "foundationModels",
"model_name": "jamba-mini",
"model_version": "v1",
"certifications": [
"GDPR",
"CCPA",
"PCI DSS",
"HIPAA",
"SOC 2 Type 2",
"ISO/IEC 27001",
"ISO/IEC 27017",
"ISO/IEC 27018",
"ISO 42001"
],
"model_config": {
"model_provider": "ai21",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.ai21.com/jamba/",
"endpoint": {
"scheme": "https",
"host": "api.ai21.com",
"port": 443,
"base_path": "/studio/v1"
},
"paths": {
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 0.4,
"top_p": 1,
"top_k": null
}
}
},
"fireworks": {
"testing_for": "foundationModels",
"model_name": "accounts/fireworks/models/llama-v3p1-8b-instruct",
"model_version": "v1",
"certifications": [
"HIPAA",
"SOC 2 Type 2"
],
"model_config": {
"model_provider": "fireworks",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://fireworks.ai/",
"endpoint": {
"scheme": "https",
"host": "api.fireworks.ai",
"port": 443,
"base_path": "/inference/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"alibaba": {
"testing_for": "foundationModels",
"model_name": "qwen-plus",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "alibaba",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.alibabacloud.com/help/en/model-studio",
"endpoint": {
"scheme": "https",
"host": "dashscope-intl.aliyuncs.com",
"port": 443,
"base_path": "/compatible-mode/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": null,
"top_p": null,
"top_k": null
}
}
},
"portkey": {
"testing_for": "foundationModels",
"model_name": "gpt-4o",
"model_version": "v1",
"certifications": [
"GDPR",
"HIPAA",
"SOC 2 Type 2",
"ISO 27001:2022"
],
"model_config": {
"model_provider": "portkey",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://portkey.ai/",
"endpoint": {
"scheme": "https",
"host": "api.portkey.ai",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"deepseek": {
"testing_for": "foundationModels",
"model_name": "deepseek-chat",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "deepseek",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://www.deepseek.com/",
"endpoint": {
"scheme": "https",
"host": "api.deepseek.com",
"port": 443,
"base_path": ""
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2.5,
"output_cost_1M_tokens": 10
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"mistral": {
"testing_for": "foundationModels",
"model_name": "mistral-large-latest",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "mistral",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://mistral.ai",
"endpoint": {
"scheme": "https",
"host": "api.mistral.ai",
"port": 443,
"base_path": "/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": 2,
"output_cost_1M_tokens": 6,
"mistral_format": "openai"
},
"default_request_options": {
"temperature": null,
"top_p": 1,
"top_k": null
}
}
},
"llama": {
"testing_for": "foundationModels",
"model_name": "meta-llama/Llama-2-7b-chat-hf",
"model_version": "v1",
"certifications": [],
"model_config": {
"model_provider": "llama",
"hosting_type": "External",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"model_source": "https://llama.com",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/models/{model_name}/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"llama2_format": "openai"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
},
"custom": {
"testing_for": "agents",
"certifications": [],
"model_config": {
"model_provider": "custom",
"hosting_type": "External",
"model_source": "https://huggingface.co",
"endpoint": {
"scheme": "https",
"host": "api-inference.huggingface.co",
"port": 443,
"base_path": "/agents/v1"
},
"paths": {
"completions": "/completions",
"chat": "/chat/completions"
},
"auth_data": {
"header_name": "Authorization",
"header_prefix": "Bearer",
"space_after_prefix": true
},
"input_modalities": [
"text",
"image",
"audio"
],
"output_modalities": [
"text"
],
"tools": [
{
"name": "web_search",
"description": "The tool web search is used to search the web for information related to finance."
}
],
"custom_headers": [
{
"key": "test",
"value": "test"
}
],
"custom_payload": {
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "{prompt}"
}
]
},
"custom_response_content_type": "json",
"custom_response_format": ".choices[0].message.content",
"metadata": {
"max_tokens": 500,
"input_cost_1M_tokens": null,
"output_cost_1M_tokens": null,
"llama2_format": "openai"
},
"default_request_options": {
"temperature": 1,
"top_p": 1,
"top_k": null
}
}
}
}