Why Together AI
Together hosts the open-weight catalogue behind an OpenAI-compatible endpoint without forcing you to operate vLLM yourself. Useful when you want open-weight quality plus reproducibility but do not want to maintain GPU infrastructure. The pricing model is straightforward per-token across the catalogue.
Models worth knowing about
premium
meta-llama/Llama-3.3-70B-Instruct-Turbo
General coordinator
specialty
Qwen/Qwen2.5-Coder-32B-Instruct
Coding agents
fast
deepseek-ai/DeepSeek-V3
Cheaper alternative to direct DeepSeek
Strengths
- Hosted open-weight catalogue without operational overhead
- OpenAI-compatible API, drop-in
- Wide model selection, including fine-tuned variants
- Predictable per-token pricing
Worth knowing
- No first-class entry in the credential catalog yet, configure via inline env template
- Latency higher than dedicated infrastructure
- Quality matches the underlying model, no special tuning
- Some quotas at lower tiers
Drop into your app.yaml
agent brain block
1brain:2 provider: openai_compat3 model: meta-llama/Llama-3.3-70B-Instruct-Turbo4 config:5 base_url: "https://api.together.xyz/v1"6 api_key: "{{env.TOGETHER_API_KEY}}"7 temperature: 0.2⚡ Inline config (catalog support pending)
Together AIdoesn't have a first-class catalog entry yet. Configure it inline using env templates, the same way the blog examples show. Native catalog support is on the roadmap.
TOGETHER_API_KEYTogether AI API key# add to ~/.digitorn/.env
TOGETHER_API_KEY=...Run one in 5 minutes
Install Digitorn and chat with your Together AI agent
# 1. install the runtime
curl -sSL https://digitorn.ai/install | sh
# 2. drop your Together AI key in the env file
echo 'TOGETHER_API_KEY=...' >> ~/.digitorn/.env
# 3. install a starter agent and chat
digitorn install hub://digitorn/digitorn-code
digitorn chat digitorn-codeNewsletter
Get the next post in your inbox.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.
Other providers Digitorn supports
frontierAnthropic Claude/integrations/anthropicfrontierOpenAI/integrations/openaifastDeepSeek/integrations/deepseekfrontierMistral/integrations/mistralopenOllama/integrations/ollamaopenvLLM/integrations/vllmfastGroq/integrations/groqenterpriseAzure OpenAI/integrations/azure-openaifrontierGoogle Gemini/integrations/google-gemini