Azure OpenAI · chat
Llama-4-Maverick-17B-128E-Instruct-FP8
azure/Llama-4-Maverick-17B-128E-Instruct-FP8
- Input price
- $1.41 / 1M tokens
- Output price
- $0.350 / 1M tokens
- Context window
- 1M tokens
- Lifecycle
- stable
Llama-4-Maverick-17B-128E-Instruct-FP8 for OpenAI-compatible gateway routing
Llama-4-Maverick-17B-128E-Instruct-FP8 is a Azure OpenAI chat model in the Ferro Labs live catalog with a 1M tokens context window, 16K tokens maximum output, and capabilities including Vision, Function Calling, and JSON Mode, and more.
Token pricing is listed as $1.41 / 1M tokens for input tokens and $0.350 / 1M tokens for output tokens. Route calls through the Ferro Labs AI Gateway by sending model as azure/Llama-4-Maverick-17B-128E-Instruct-FP8 to the OpenAI-compatible chat completions endpoint. The catalog lists this model as stable for normal gateway routing.
OpenAI-compatible usage example
curl https://api.ferrolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $GATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "azure/Llama-4-Maverick-17B-128E-Instruct-FP8", "messages": [{"role": "user", "content": "Hello!"}]}'
Capabilities
- Vision
- Function Calling
- JSON Mode
- Streaming
Modalities
Input
- Text
- Image
Output
- Text
More from Azure OpenAI
Catalog prices may change. Verify current provider terms before purchasing.