jishie

Qwen3.5 397B-A17B

aihubmix/qwen3.5-397b-a17b · family qwen · in: text, image, video, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio.

$0.37
Blended $/1M (3:1)
$0.1644
Input $/1M
$0.9864
Output $/1M
$1.15
1M in + 1M out
—
Cache read $/1M
#2426 of 7,795
Cheapest rank
Provider
AIHubMix (aihubmix)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video audio

Same model, other providers

“Qwen3.5 397B-A17B” is offered by 19 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
UnoRouterfreefree$0.00262k
AIHubMix (this)$0.1644$0.9864$0.37262k
EmpirioLabs AI$0.172$1.03$0.39256k
OrcaRouter$0.172$1.03$0.39262k
Alibaba (China)$0.172$1.03$0.39262k
CrofAI$0.35$1.75$0.70262k
Vultr$0.3$2$0.72262k
SiliconFlow$0.39$2.34$0.88262k
Kilo Gateway$0.39$2.34$0.88262k
TokenGo$0.4$2.65$0.96262k
OpenRouter$0.55$3.5$1.29262k
Ofox$0.55$3.5$1.29256k
LLMTR$0.6$3.6$1.35256k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3.5-397b-a17b","messages":[{"role":"user","content":"hello"}]}'

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

← all AIHubMix models · model index · JSON