jishie

Hy4 flash

huggingface/tencent/Hy4-flash · family Hy · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$0.06
Blended $/1M (3:1)
$0.035
Input $/1M
$0.1405
Output $/1M
$0.18
1M in + 1M out
—
Cache read $/1M
#749 of 9,507
Cheapest rank
Provider
Hugging Face (huggingface)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Hy4 flash” is offered by 6 providers — cheapest-effective first. This one (Hugging Face) is the cheapest.

ProviderInputOutputBlendedContext
Hugging Face (this)$0.035$0.1405$0.061M
OpenRouter$0.035$0.1405$0.061M
Novita AI$0.07$0.281$0.121M
DevPass (LLM Gateway)$0.07$0.281$0.121M
Kenari$0.0714$0.2857$0.131M
CrossModel$0.08$0.32$0.141M

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"tencent/Hy4-flash","messages":[{"role":"user","content":"hello"}]}'

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

← all Hugging Face models · model index · JSON