Together AI Provider
Together AI is a platform for running large language models in the cloud with fast inference.
Available Models
MiniMax M2.5
together.ai/minimax-m2.5Context Size
228.7k
Stability
STABLEPricing
Input
$0.30/M
Cached
—/M
Output
$1.20/M
Capabilities
Streaming
Reasoning
JSON Output
GLM-5
together.ai/glm-5Context Size
202.8k
Stability
STABLEPricing
Input
$1.00/M
Cached
—/M
Output
$3.20/M
Capabilities
Streaming
Tools
Reasoning
JSON Output
Kimi K2.5
together.ai/kimi-k2.5Context Size
262.1k
Stability
STABLEPricing
Input
$0.50/M
Cached
—/M
Output
$2.80/M
Capabilities
Streaming
Vision
GLM-4.7
together.ai/glm-4.7Context Size
202.8k
Stability
STABLEPricing
Input
$0.45/M
Cached
—/M
Output
$2.00/M
Capabilities
Streaming
Reasoning
Llama 4 Scout
together.ai/llama-4-scoutContext Size
32.8k
Stability
unstablePricing
Input
$0.18/M
Cached
—/M
Output
$0.59/M
Capabilities
Streaming
Tools
Llama 3.1 8B Instruct
together.ai/llama-3.1-8b-instructContext Size
128k
Stability
STABLEPricing
Input
$0.06/M
Cached
—/M
Output
$0.06/M
Capabilities
Streaming
Tools
Gemma 2 27B IT
together.ai/gemma-2-27b-it-togetherContext Size
8.2k
Stability
STABLEPricing
Input
$0.08/M
Cached
—/M
Output
$0.08/M
Capabilities
Streaming
Mixtral 8x7B Instruct
together.ai/mixtral-8x7b-instruct-togetherContext Size
32.8k
Stability
STABLEPricing
Input
$0.06/M
Cached
—/M
Output
$0.06/M
Capabilities
Streaming
JSON Output
Mistral 7B Instruct
together.ai/mistral-7b-instruct-togetherContext Size
8.2k
Stability
STABLEPricing
Input
$0.06/M
Cached
—/M
Output
$0.06/M
Capabilities
Streaming
JSON Output