jishie

Hy3

siliconflow/tencent/Hy3 · family Hy · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.23
Blended $/1M (3:1)
$0.132
Input $/1M
$0.528
Output $/1M
$0.66
1M in + 1M out
$0.033 −75%
Cache read $/1M
#1790 of 7,461
Cheapest rank
Provider
SiliconFlow (siliconflow)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
tools reasoning text

Same model, other providers

“Hy3” is offered by 16 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.00256k
Tencent TokenHubfreefree$0.00256k
Tencent Token Planfreefree$0.00256k
Kilo Gateway$0.0825$0.33$0.14262k
OpenRouter$0.0825$0.33$0.14262k
SiliconFlow (this)$0.132$0.528$0.23262k
DevPass (LLM Gateway)$0.132$0.528$0.23262k
Requesty$0.14$0.58$0.25262k
Hugging Face$0.14$0.58$0.25262k
Vercel AI Gateway$0.14$0.58$0.25262k
Jalapeno Cloud$0.14$0.58$0.25203k
Deep Infra$0.14$0.58$0.25262k
OpenCode Go$0.14$0.58$0.25256k

Call it

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

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

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

← all SiliconFlow models · model index · JSON