Hy3

vercel/tencent/hy3 · family hy3 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.25Blended $/1M (3:1)

$0.14Input $/1M

$0.58Output $/1M

$0.721M in + 1M out

$0.035 −75%Cache read $/1M

#1486 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 262,144 tokens
Max output: 262,144 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“Hy3” is offered by 9 providers — cheapest-effective first. Tencent TokenHub is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Tencent TokenHub	free	free	$0.00	256k
Tencent Token Plan	free	free	$0.00	256k
OpenRouter	$0.132	$0.528	$0.23	262k
Vercel AI Gateway (this)	$0.14	$0.58	$0.25	262k
OpenCode Go	$0.14	$0.58	$0.25	256k
LLM Gateway	$0.14	$0.58	$0.25	262k
Kilo Gateway	$0.14	$0.58	$0.25	262k
Hugging Face	$0.14	$0.58	$0.25	262k
Deep Infra	$0.14	$0.58	$0.25	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway 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):