Name: Llama-3 70B Gradient Instruct 1048k API
Brand: Gradient

How to use Llama-3 70B Gradient Instruct 1048k 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-3 70B Gradient Instruct 1048k API Pricing

Type	Price
Input
Output

Model	Input	Output	Context	Best for
Llama-3 70B Gradient Instruct 1048k This page
GPT-5.5	$6.5 / 1M tokens	$39 / 1M tokens	1.05M tokens	Reasoning + agents
Claude Sonnet 5	$2.6 / 1M tokens	$13 / 1M tokens	1M tokens	Balanced coding + agents
Kimi K3	$3.9 / 1M tokens	$19.5 / 1M tokens	1M tokens	Long-context, multimodal & agentic workflows
Gemini 3.5 Flash	$0.65 / 1M tokens	$3.9 / 1M tokens	1.05M tokens	Reasoning + agents

Yes, Llama-3 70B Gradient Instruct 1048k can stream responses as they are generated.

Yes, Llama-3 70B Gradient Instruct 1048k supports both function calling and structured outputs.

Llama-3 70B Gradient Instruct 1048k was built by Gradient.