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.

$2.72
Blended $/1M (3:1)
$1.82
Input $/1M
$5.45
Output $/1M
$7.26
1M in + 1M out
$0.17 −91%
Cache read $/1M
#4548 of 6,273
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 18 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Deep Infra$1.65$4.95$2.48256k
AIHubMix$1.69$5.07$2.54991k
Alibaba (China)$1.78$5.33$2.671M
SCX.ai (this)$1.82$5.45$2.721M
CrossModel$1.88$5.63$2.821M
NanoGPT$2$6$3.00991k
OpenRouter$2$6$3.001M
OpenCode Go$2$6$3.001M
Merge Gateway$2$6$3.001M
Alibaba$2$6$3.001M
Ofox$2$6$3.001M

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