jishie

Qwen3-Next 80B-A3B (Thinking)

edenai/qwen/qwen3-next-80b-a3b-thinking · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.41
Blended $/1M (3:1)
$0.15
Input $/1M
$1.2
Output $/1M
$1.35
1M in + 1M out
Cache read $/1M
#1968 of 6,123
Cheapest rank
Provider
Eden AI (edenai)
Kind
text (outputs text)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text

Same model, other providers

“Qwen3-Next 80B-A3B (Thinking)” is offered by 7 providers — cheapest-effective first. Cortecs is the cheapest at $0.41 blended.

ProviderInputOutputBlendedContext
Cortecs$0.149$1.2$0.41128k
Eden AI (this)$0.15$1.2$0.41131k
OpenRouter$0.15$1.2$0.41262k
LLM Gateway$0.15$1.2$0.41131k
Kilo Gateway$0.15$1.2$0.41131k
Alibaba (China)$0.144$1.43$0.47131k
Alibaba$0.5$6$1.88131k

Call it

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

Most providers are OpenAI-compatible — point base_url at Eden AI 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-thinking","messages":[{"role":"user","content":"hello"}]}'

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

← all Eden AI models · model index · JSON