Qwen: Qwen3 Next 80B A3B Thinking, Qwen — route, pricing & source
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...
OpenRoutermediumLast checked: May 14, 2026
Input
$0.0975 / 1M
/ 1M tokens
Output
$0.7800 / 1M
/ 1M tokens
Cached input
Not available
Not available
Cache write
Not available
Not available
Context and limits
Context window
131.1K
Max output
32,768
Input modalities
text
Output modalities
text
Weight access
Unknown
Availability
Unknown
Capability flags
ToolsJSONReasoningLong context
From source metadata + verification fields — confirm provider docs before production.
Benchmarks
No safely merged benchmark result for this model yet.
Access and license
Official API
No
Open weights
No
Self-hostable
No
License
Unknown
Example costs
Scenario: 1K input + 300 output tokens / request
10,000 requests
$3.32
100,000 requests
$33.15
1,000,000 requests
$331.50
Cheaper alternatives
Lower-cost models for the same scenario
