jishie

Qwen3.5 397B-A17B

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

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#459 of 8,512
Cheapest rank
Provider
UnoRouter (unorouter)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.5 397B-A17B” is offered by 20 providers — cheapest-effective first. This one (UnoRouter) is the cheapest.

ProviderInputOutputBlendedContext
UnoRouter (this)freefree$0.00262k
AIHubMix$0.1644$0.9864$0.37262k
OrcaRouter$0.172$1.03$0.39262k
Alibaba (China)$0.172$1.03$0.39262k
EmpirioLabs AI$0.172$1.03$0.39258k
Kilo Gateway$0.39$2.34$0.88256k
SiliconFlow$0.39$2.34$0.88262k
TokenGo$0.4$2.65$0.96262k
NEAR AI Cloud$0.5$3.3$1.20262k
Ofox$0.55$3.5$1.29256k
Cloudflare AI Gateway$0.6$3.6$1.35262k
Novita AI$0.6$3.6$1.35262k
Jalapeno Cloud$0.6$3.6$1.35262k

Call it

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

Most providers are OpenAI-compatible — point base_url at UnoRouter 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:free","messages":[{"role":"user","content":"hello"}]}'

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

← all UnoRouter models · model index · JSON