All Vendors
Together AI
FeaturedLLM Inference
Fast, affordable inference for open-source models. Run Llama, Mistral, and other popular models through a simple API.
Visit Site
$0.20-2.00/1M tokens
Details
- Pricing Model
- usage-based
- Affiliate Program
- yes
- Commission
- 20% recurring
Specs
- input price per million
- 0.2
- max context
- 128K
- models
- Llama 3, Mistral, Mixtral, Qwen, DeepSeek
- output price per million
- 0.6
Best value for open-source model inference. Supports fine-tuning.