Name: LLaMA-2-32K (7B) API
Brand: Together

How to use LLaMA-2-32K (7B) API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to .

OpenAI-compatible — swap the base URL and it works with your existing SDK.

LLaMA-2-32K (7B) API Pricing

Type	Price
Input	$0.21 / 1M
Output	$0.21 / 1M

Model	Input	Output
LLaMA-2-32K (7B) This page	$0.21 / 1M	$0.21 / 1M
Mixtral 8x22B	$1.26 / 1M	$1.26 / 1M
LLama 3 (70B)	$0.945 / 1M	$0.945 / 1M
Llama 3 (8B)	$0.21 / 1M	$0.21 / 1M
Falcon (40B)	$0.84 / 1M	$0.84 / 1M

LLaMA-2-32K (7B) is priced at input $0.21 / 1M, output $0.21 / 1M.

Yes, LLaMA-2-32K (7B) can stream responses as they are generated.

Yes, LLaMA-2-32K (7B) supports both function calling and structured outputs.

LLaMA-2-32K (7B) was built by Together.

It is served via the v1 endpoint from Together.