AI Workflow MCP

browse · models · azure_ai

Llama 4 Maverick 17B 128E Instruct FP8

azure_ai model — context 1M, capabilities: .

All models

Specs

Model IDazure-ai-llama-4-maverick-17b-128e-instruct-fp8
Providerazure_ai
Familyllama-4
Statusactive
Input $/MTok$1.41
Output $/MTok$0.35
Cache read $/MTok—
Cache write $/MTok—
Context window1,000,000 tokens (1M)
Max output16,384 tokens (16K)
Input modalities
text
Output modalities
text
Capabilities
Supported parameters
max_tokenstemperaturetop_p
Knowledge cutoff1970-01
Release date1970-01-01
Last synced2026-05-13
Deprecated—
Official docsOpen docs
Intelligence indexnot measured
Throughput—

Call via MCP

// claude-desktop / cursor / windsurf
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "id": 1,
  "params": {
    "name": "get_model_pricing",
    "arguments": { "model_id": "azure-ai-llama-4-maverick-17b-128e-instruct-fp8" }
  }
}

Call via REST

curl -X POST https://mcp.aiworkflowmcp.com/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tools/call","id":1,"params":{"name":"get_model_pricing","arguments":{"model_id":"azure-ai-llama-4-maverick-17b-128e-instruct-fp8"}}}'