meta/llama-4.1-behemoth-2t

Trillion-parameter MoE teacher model now served broadly.

TextImageLong contextReasoningAgents & toolsopen-sourcelong-contexttools

Specifications

Context window: 1.049M
Max output tokens: 32,768
Released: 2025-10
Infra providers: 5
Throughput: 98 tok/s
Latency (TTFB, sample): 520 ms
Capabilities: Supports tools

Pricing

per million tokens

Input

$0.75

Output

$1.00

Blended (3:1)

$0.81

Use this model

Works with any OpenAI SDK — same request shape, different model id.

curl https://api.lokarouter.id/v1/chat/completions \  -H "Authorization: Bearer sk-lkr-your-key" \  -H "Content-Type: application/json" \  -d '{    "model": "meta/llama-4.1-behemoth-2t",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Sample data for demonstration — connect your workspace for live stats.