Llama 3.3 70B

FAST

Meta · meta/llama-3.3-70b

Available

Widely deployed open-weight model with predictable behaviour and permissive licensing for self-host parity.

Input / 1M tokens

৳36

Output / 1M tokens

৳48

Context length

128K

Max output

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

Suitable for

Fast
Coding
Low Cost

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-3.3-70b",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput126 tok/s

Time to first token0.7s

StreamingSupported

Tool callingSupported

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

Routing

Primary routeMeta direct

FallbackSecondary region

Prompt retentionNot retained