jishie

Qwen3 Next 80B A3B Thinking

vercel/alibaba/qwen3-next-80b-a3b-thinking · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.41Blended $/1M (3:1)
$0.15Input $/1M
$1.2Output $/1M
$1.351M in + 1M out
Cache read $/1M
#1962 of 5,000Cheapest rank
Provider
Vercel AI Gateway (vercel)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“Qwen3 Next 80B A3B Thinking” is offered by 4 providers — cheapest-effective first. This one (Vercel AI Gateway) is the cheapest.

ProviderInputOutputBlendedContext
Vercel AI Gateway (this)$0.15$1.2$0.41131k
Merge Gateway$0.15$1.2$0.41131k
NovitaAI$0.15$1.5$0.49131k
Jiekou.AI$0.15$1.5$0.4966k

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":"alibaba/qwen3-next-80b-a3b-thinking","messages":[{"role":"user","content":"hello"}]}'

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