Skip to main content

Together AI

Access hundreds of open-source models through Together's inference API.

Configuration

FieldRequiredExample
Application NameYesmy-together-app
Model NameYesmeta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
API KeyYesYour Together API key

Getting Your API Key

  1. Go to Together AI
  2. Sign up or log in
  3. Navigate to SettingsAPI Keys
  4. Copy your API key
ModelDescription
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Llama 4 flagship MoE model (400B params, 17B active)
meta-llama/Llama-4-Scout-17B-16E-InstructLlama 4 multimodal with 10M context
deepseek-ai/DeepSeek-V3.1Hybrid thinking/non-thinking mode (671B params)
deepseek-ai/DeepSeek-R1Full reasoning model (87.5% AIME)
deepseek-ai/DeepSeek-R1-Distill-Llama-70BFree distilled reasoning model
Qwen/Qwen3-235B-A22B-Instruct-2507Latest Qwen3 with 1M token context
meta-llama/Llama-3.3-70B-Instruct-TurboHigh-quality text model

For the complete list of 200+ available models, visit the Together AI Models and API Reference.

Advanced Parameters

ParameterTypeDescription
max_tokensintegerMaximum tokens in response
temperaturefloatRandomness
top_pfloatNucleus sampling
top_kintegerTop-k sampling
repetition_penaltyfloatPenalize repetition
stoparrayStop sequences

Setup Steps

  1. Navigate to AI Applications → New Application
  2. Select Model Providers tab
  3. Click Together
  4. Enter your Application Name and API Key
  5. Select your desired Model Name
  6. Configure Advanced Settings (optional)
  7. Click Test Response to verify (optional)
  8. Review and submit