jishie

Hy3 preview

zenmux/tencent/hy3-preview · family Hy · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.27
Blended $/1M (3:1)
$0.172
Input $/1M
$0.572
Output $/1M
$0.74
1M in + 1M out
$0.058 −66%
Cache read $/1M
#2107 of 7,713
Cheapest rank
Provider
ZenMux (zenmux)
Kind
text (outputs text)
Context
256,000 tokens
Max output
64,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Hy3 preview” is offered by 5 providers — cheapest-effective first. Tencent TokenHub is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Tencent TokenHubfreefree$0.00256k
AIHubMix$0.17$0.5667$0.27256k
ZenMux (this)$0.172$0.572$0.27256k
Kilo Gateway$0.18$0.6$0.29262k
OpenRouter$0.18$0.6$0.29262k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"tencent/hy3-preview","messages":[{"role":"user","content":"hello"}]}'

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

← all ZenMux models · model index · JSON