Qwen3 Next 80B A3B Instruct

merge-gateway/qwen/qwen3-next-80b-a3b-instruct · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

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

$0.144Input $/1M

$0.574Output $/1M

$0.721M in + 1M out

$0.0288 −80%Cache read $/1M

#1497 of 5,000Cheapest rank

Provider: Merge Gateway (merge-gateway)
Context: 131,072 tokens
Max output: 32,768 tokens
Capabilities: toolstext

Same model, other providers

“Qwen3 Next 80B A3B Instruct” is offered by 5 providers — cheapest-effective first. This one (Merge Gateway) is the cheapest.

Provider	Input	Output	Blended	Context
Merge Gateway (this)	$0.144	$0.574	$0.25	131k
Vercel AI Gateway	$0.15	$1.2	$0.41	131k
Helicone	$0.14	$1.4	$0.45	262k
NovitaAI	$0.15	$1.5	$0.49	131k
Jiekou.AI	$0.15	$1.5	$0.49	66k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Merge Gateway 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-next-80b-a3b-instruct","messages":[{"role":"user","content":"hello"}]}'

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