Qwen3 32B

huggingface/Qwen/Qwen3-32B · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.36Blended $/1M (3:1)

$0.29Input $/1M

$0.59Output $/1M

$0.881M in + 1M out

—Cache read $/1M

#1860 of 5,000Cheapest rank

Provider: Hugging Face (huggingface)
Context: 131,072 tokens
Max output: 16,384 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“Qwen3 32B” is offered by 9 providers — cheapest-effective first. OpenRouter is the cheapest at $0.13 blended.

Provider	Input	Output	Blended	Context
OpenRouter	$0.08	$0.28	$0.13	131k
Deep Infra	$0.08	$0.28	$0.13	41k
Abacus	$0.09	$0.29	$0.14	131k
Cortecs	$0.099	$0.299	$0.15	40k
LLM Gateway	$0.1	$0.3	$0.15	41k
Kilo Gateway	$0.104	$0.416	$0.18	41k
NovitaAI	$0.1	$0.45	$0.19	41k
Jiekou.AI	$0.1	$0.45	$0.19	41k
Hugging Face (this)	$0.29	$0.59	$0.36	131k

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":"Qwen/Qwen3-32B","messages":[{"role":"user","content":"hello"}]}'

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