jishie

Qwen3.6 Max Preview

empiriolabs/qwen3-6-max-preview · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$2.95Blended $/1M (3:1)
$1.31Input $/1M
$7.88Output $/1M
$9.191M in + 1M out
$1.31Cache read $/1M
#4257 of 5,000Cheapest rank
Provider
EmpirioLabs AI (empiriolabs)
Context
256,000 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“Qwen3.6 Max Preview” is offered by 9 providers — cheapest-effective first. Kilo Gateway is the cheapest at $2.31 blended.

ProviderInputOutputBlendedContext
Kilo Gateway$1.027$6.162$2.31262k
OpenRouter$1.027$6.162$2.31262k
NanoGPT$1.04$6.24$2.34246k
Pioneer$1.04$6.24$2.34262k
AIHubMix$1.27$7.61$2.85240k
LLM Gateway$1.3$7.8$2.92262k
Alibaba$1.3$7.8$2.92262k
EmpirioLabs AI (this)$1.31$7.88$2.95256k
Merge Gateway$1.31$7.88$2.95256k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at EmpirioLabs AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3-6-max-preview","messages":[{"role":"user","content":"hello"}]}'

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