Padma
← All models

Qwen3.5 397B-A17B

Qwen · qwen/qwen3.5-397b-a17b

Coming soon

Largest open-weight Qwen3.5: a 397B-total, 17B-active vision-language MoE.

Not callable yet: Padma has not connected Qwen on this server. The price is real; requests answer 503 model_unavailable, and are not charged, until it is.

Input / 1M tokens

৳73.81

Output / 1M tokens

৳442.84

Cached input / 1M

no discount

Context length

262.144K

Max output

65.536K

Provider list price: $0.60 in · $3.60 out per 1M tokens (Qwen), × ৳123.01 per dollar. No markup. Prompt tokens the provider writes to its cache: ৳92.26 per 1M.

Suitable for

  • Reasoning
  • Coding
  • Vision

Example request

cURL
curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.5-397b-a17b",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Performance

Throughput60 tok/s
Time to first token1.5s
StreamingSupported
Tool callingSupported

Typical figures for this model, which the auto/* routers score on — not a guarantee for any one request.

Routing

Primary routeQwen direct
Fallback hostsNone — one host
Prompt retentionPadma keeps none unless you turn on payload logging; the provider's own API terms apply