Wide open-source model catalog with serverless + dedicated
Together AI — Wide open-source model catalog with serverless + dedicated.
Free tier: $1 free credit on signup. A few "free" tagged endpoints (Llama-3.3-70B-Instruct-Turbo-Free) with strict 60/min rate limit.
API is OpenAI-compatible — point your SDK at https://api.together.xyz/v1.
meta-llama/Llama-3.3-70B-Instruct-Turbometa-llama/Meta-Llama-3.1-405B-Instruct-Turbomistralai/Mixtral-8x7B-Instruct-v0.1deepseek-ai/DeepSeek-V3Pay-per-token; 70B Turbo $0.88/1M tokens, 405B $3.50/1M, smaller models cheaper. Together fine-tuning + dedicated endpoints available.
Reserved instances, BYO infra, and SOC 2 / HIPAA tiers.
https://api.together.xyz/v1
OpenAI-compatible — works with the OpenAI SDK by overriding base_url.
curl https://api.together.xyz/v1/chat/completions \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
"messages": [{"role": "user", "content": "Hello in 5 words"}]
}'
Open-source-first stacks. Use when you want Llama 3.1 405B, DeepSeek V3, or to fine-tune.
Closed-model needs (GPT-4, Claude). Use OpenRouter or direct provider.
$1 free credit on signup. A few "free" tagged endpoints (Llama-3.3-70B-Instruct-Turbo-Free) with strict 60/min rate limit. No credit card is required to sign up.
Most commonly used: meta-llama/Llama-3.3-70B-Instruct-Turbo, meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo, mistralai/Mixtral-8x7B-Instruct-v0.1, deepseek-ai/DeepSeek-V3. The full current list is on Together AI's docs page.
Yes — point the OpenAI SDK's base URL at `https://api.together.xyz/v1` and pass your Together AI API key.
Pay-per-token; 70B Turbo $0.88/1M tokens, 405B $3.50/1M, smaller models cheaper. Together fine-tuning + dedicated endpoints available. If your traffic is bursty or seasonal, the free tier may be enough; if you need a guaranteed SLA, upgrade.