jishie

Hy3

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

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
Cache read $/1M
#205 of 6,950
Cheapest rank
Provider
Kenari (kenari)
Kind
text (outputs text)
Context
256,000 tokens
Max output
64,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Hy3” is offered by 13 providers — cheapest-effective first. This one (Kenari) is the cheapest.

ProviderInputOutputBlendedContext
Kenari (this)freefree$0.00256k
Tencent TokenHubfreefree$0.00256k
Tencent Token Planfreefree$0.00256k
OpenRouter$0.132$0.528$0.23262k
Vercel AI Gateway$0.132$0.528$0.23256k
Jalapeno Cloud$0.14$0.58$0.25203k
Deep Infra$0.14$0.58$0.25262k
Hugging Face$0.14$0.58$0.25262k
Requesty$0.14$0.58$0.25262k
DevPass (LLM Gateway)$0.14$0.58$0.25262k
Kilo Gateway$0.14$0.58$0.25262k
CrossModel$0.16$0.64$0.28262k
OrcaRouter$0.18$0.59$0.28256k

Call it

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

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

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

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

← all Kenari models · model index · JSON