together.ai

together.ai API key: api.together.xyz/settings/api-keys

Notes:

Known: icon provided.
Known issue: fetching list of models is not supported.
The example includes a model list, which was last updated on August 1, 2024, for your convenience.

🔥

Fetch and order the models▷

This python script can fetch and order the llm models for you. The output will be saved in models.txt, formated in a way that should make it easier for you to include in the yaml config.

fetch_togetherai.py

import json
 
import requests
 
# API key
api_key = ""
 
# API endpoint
url = "https://api.together.xyz/v1/models"
 
# headers
headers = {
    "accept": "application/json",
    "Authorization": f"Bearer {api_key}"
}
 
# make request
response = requests.get(url, headers=headers)
 
# parse JSON response
data = response.json()
 
# extract an ordered list of unique model IDs
model_ids = sorted(
    [
        model['id']
        for model in data
        if model['type'] == 'chat'
    ]
)
 
# write result to a text file
with open("models_togetherai.json", "w") as file:
    json.dump(model_ids, file, indent=2)

    - name: "together.ai"
      apiKey: "${TOGETHERAI_API_KEY}"
      baseURL: "https://api.together.xyz"
      models:
        default: [
          "Austism/chronos-hermes-13b",
          "Gryphe/MythoMax-L2-13b",
          "HuggingFaceH4/zephyr-7b-beta",
          "NousResearch/Hermes-2-Theta-Llama-3-70B",
          "NousResearch/Nous-Capybara-7B-V1p9",
          "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
          "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
          "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
          "NousResearch/Nous-Hermes-2-Yi-34B",
          "NousResearch/Nous-Hermes-Llama2-13b",
          "NousResearch/Nous-Hermes-Llama2-70b",
          "NousResearch/Nous-Hermes-llama-2-7b",
          "Open-Orca/Mistral-7B-OpenOrca",
          "Qwen/Qwen1.5-0.5B-Chat",
          "Qwen/Qwen1.5-1.8B-Chat",
          "Qwen/Qwen1.5-110B-Chat",
          "Qwen/Qwen1.5-14B-Chat",
          "Qwen/Qwen1.5-32B-Chat",
          "Qwen/Qwen1.5-4B-Chat",
          "Qwen/Qwen1.5-72B-Chat",
          "Qwen/Qwen1.5-7B-Chat",
          "Qwen/Qwen2-1.5B",
          "Qwen/Qwen2-1.5B-Instruct",
          "Qwen/Qwen2-72B",
          "Qwen/Qwen2-72B-Instruct",
          "Qwen/Qwen2-7B",
          "Qwen/Qwen2-7B-Instruct",
          "Snowflake/snowflake-arctic-instruct",
          "Undi95/ReMM-SLERP-L2-13B",
          "Undi95/Toppy-M-7B",
          "WizardLM/WizardLM-13B-V1.2",
          "allenai/OLMo-7B-Instruct",
          "carson/ml31405bit",
          "carson/ml3170bit",
          "carson/ml318bit",
          "carson/ml318br",
          "codellama/CodeLlama-13b-Instruct-hf",
          "codellama/CodeLlama-34b-Instruct-hf",
          "codellama/CodeLlama-70b-Instruct-hf",
          "codellama/CodeLlama-7b-Instruct-hf",
          "cognitivecomputations/dolphin-2.5-mixtral-8x7b",
          "databricks/dbrx-instruct",
          "deepseek-ai/deepseek-coder-33b-instruct",
          "deepseek-ai/deepseek-llm-67b-chat",
          "garage-bAInd/Platypus2-70B-instruct",
          "google/gemma-2-27b-it",
          "google/gemma-2-9b-it",
          "google/gemma-2b-it",
          "google/gemma-7b-it",
          "gradientai/Llama-3-70B-Instruct-Gradient-1048k",
          "lmsys/vicuna-13b-v1.3",
          "lmsys/vicuna-13b-v1.5",
          "lmsys/vicuna-13b-v1.5-16k",
          "lmsys/vicuna-7b-v1.3",
          "lmsys/vicuna-7b-v1.5",
          "meta-llama/Llama-2-13b-chat-hf",
          "meta-llama/Llama-2-70b-chat-hf",
          "meta-llama/Llama-2-7b-chat-hf",
          "meta-llama/Llama-3-70b-chat-hf",
          "meta-llama/Llama-3-8b-chat-hf",
          "meta-llama/Meta-Llama-3-70B-Instruct",
          "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
          "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3-8B-Instruct",
          "meta-llama/Meta-Llama-3-8B-Instruct-Lite",
          "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-70B-Instruct-Reference",
          "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-70B-Reference",
          "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference",
          "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
          "microsoft/WizardLM-2-8x22B",
          "mistralai/Mistral-7B-Instruct-v0.1",
          "mistralai/Mistral-7B-Instruct-v0.2",
          "mistralai/Mistral-7B-Instruct-v0.3",
          "mistralai/Mixtral-8x22B-Instruct-v0.1",
          "mistralai/Mixtral-8x7B-Instruct-v0.1",
          "openchat/openchat-3.5-1210",
          "snorkelai/Snorkel-Mistral-PairRM-DPO",
          "teknium/OpenHermes-2-Mistral-7B",
          "teknium/OpenHermes-2p5-Mistral-7B",
          "togethercomputer/CodeLlama-13b-Instruct",
          "togethercomputer/CodeLlama-34b-Instruct",
          "togethercomputer/CodeLlama-7b-Instruct",
          "togethercomputer/Koala-13B",
          "togethercomputer/Koala-7B",
          "togethercomputer/Llama-2-7B-32K-Instruct",
          "togethercomputer/Llama-3-8b-chat-hf-int4",
          "togethercomputer/Llama-3-8b-chat-hf-int8",
          "togethercomputer/SOLAR-10.7B-Instruct-v1.0-int4",
          "togethercomputer/StripedHyena-Nous-7B",
          "togethercomputer/alpaca-7b",
          "togethercomputer/guanaco-13b",
          "togethercomputer/guanaco-33b",
          "togethercomputer/guanaco-65b",
          "togethercomputer/guanaco-7b",
          "togethercomputer/llama-2-13b-chat",
          "togethercomputer/llama-2-70b-chat",
          "togethercomputer/llama-2-7b-chat",
          "upstage/SOLAR-10.7B-Instruct-v1.0",
          "zero-one-ai/Yi-34B-Chat"
        ]
        fetch: false # fetching list of models is not supported
      titleConvo: true
      titleModel: "togethercomputer/llama-2-7b-chat"
      summarize: false
      summaryModel: "togethercomputer/llama-2-7b-chat"
      forcePrompt: false
      modelDisplayLabel: "together.ai"

ShuttleAI Vultr Cloud Inference