Llama 5 Maverick

NEWCHEAPFAST

Meta · meta/llama-5-maverick

Available

Open-weight 600B+ MoE flagship with 2M context — longest of any frontier model. Only ~40-80B params activate per token, making inference ultra-efficient.

Input / 1M tokens

৳18

Output / 1M tokens

৳72

Context length

Max output

64K

Placeholder rates. Final pricing is published per model before launch.

Suitable for

Fast
Low Cost
Coding
Vision
Long context

Example request

cURL

curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta/llama-5-maverick",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput145 tok/s

Time to first token0.5s

StreamingSupported

Tool callingSupported

Measured from Dhaka over the last 24h of prototype traffic.

Routing

Primary routeMeta direct

FallbackSecondary region

Prompt retentionNot retained