35% offprompt cache

Qwen3.8 2.4T-A95B

qwen3.8-2.4t-a95b

Qwen3.8 2.4T-A95B — 262.144K token context, up to 1,010,000 output tokens, prompt caching.

Try in playground Get an API key

Input / output per 1M

$1.30/$3.90

official $2 / $6

Network fee$0.0010

ProviderAlibaba

ModalityText

Context

262.1K

Max output

1.0M

Input / 1M

$1.30

Output / 1M

$3.90

Pricing

Input / 1M$1.30$2

Output / 1M$3.90$6

Network fee$0.0010per request

35% below the official upstream price.

Request

POST /v1/chat/completions

curl https://api.relayrouter.org/v1/chat/completions \
  -H "Authorization: Bearer $RELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-2.4t-a95b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'