Qwen3-Next 80B-A3B (Thinking)
alibaba-cn/qwen3-next-80b-a3b-thinking · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.47
Blended $/1M (3:1)
$0.144
Input $/1M
$1.43
Output $/1M
$1.58
1M in + 1M out
—
Cache read $/1M
#2741 of 7,708
Cheapest rank
- Provider
- Alibaba (China) (
alibaba-cn) - 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 8 providers — cheapest-effective first. Kilo Gateway is the cheapest at $0.41 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kilo Gateway | $0.15 | $1.2 | $0.41 | 262k |
| OpenRouter | $0.15 | $1.2 | $0.41 | 262k |
| Merge Gateway | $0.15 | $1.2 | $0.41 | 131k |
| Eden AI | $0.15 | $1.2 | $0.41 | 131k |
| DevPass (LLM Gateway) | $0.15 | $1.2 | $0.41 | 131k |
| Alibaba (China) (this) | $0.144 | $1.43 | $0.47 | 131k |
| Jalapeno Cloud | $0.15 | $1.5 | $0.49 | 131k |
| Alibaba | $0.5 | $6 | $1.88 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Alibaba (China) and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"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):