jishie

Qwen3.8 Max

scx-ai/Qwen3.8-Max · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$2.48
Blended $/1M (3:1)
$1.65
Input $/1M
$4.99
Output $/1M
$6.64
1M in + 1M out
$0.21 −87%
Cache read $/1M
#6585 of 9,495
Cheapest rank
Provider
SCX.ai (scx-ai)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.8 Max” is offered by 36 providers — cheapest-effective first. SCNet Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
SCNet Token Planfreefree$0.001M
Alibaba Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Zenifra$1.54$4.64$2.321M
JZSTOKEN$1.56$4.67$2.341M
Vancine$1.6$4.8$2.401M
Deep Infra$1.65$4.95$2.48256k
SCX.ai (this)$1.65$4.99$2.481M
AIHubMix$1.69$5.07$2.54991k
Ofox$1.71$5.14$2.571M
TeamoRouter$1.71$5.14$2.571M
Alibaba (China)$1.78$5.33$2.671M
AbliteratedLLM$1.8$5.4$2.70262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at SCX.ai and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"Qwen3.8-Max","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all SCX.ai models · model index · JSON