Qwen3 Next 80B A3B Thinking
Openrouter textopenrouter/qwen/qwen3-next-80b-a3b-thinking
Input
$0.1500
per 1M input tokens
Output
$1.20
per 1M output tokens
Cache read
n/a
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
262,144
Max output
32,768
Effective date
Oct 3, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Oct 3, 2026 | $0.15 | $1.20 | $0.41 |
| Sep 23, 2026 | $0.15 | $1.20 | $0.41 |
| Sep 6, 2026 | $0.15 | $1.20 | $0.41 |
Qwen3 Next 80B A3B Thinking on other providers
Deepinfra
· $0.1400 in / $1.40 out
Together Ai
· $0.1500 in / $1.50 out
Gmi
· $0.1500 in / $1.50 out
Dashscope
· $0.1500 in / $1.20 out
Nebius
· $0.1500 in / $1.20 out
Qwencloud
· $0.1500 in / $1.20 out
Novita
· $0.1500 in / $1.50 out
Qwen Ai Platform
· $0.1500 in / $1.20 out
Fireworks Ai
· $0.9000 in / $0.9000 out
Other Openrouter models
openrouter/qwen/qwen3.8-27b:free
· $0.0000/Mtok out
openrouter/thinkingmachines/inkling-small:free
· $0.0000/Mtok out
openrouter/thinkingmachines/inkling:free
· $0.0000/Mtok out
openrouter/stealth/union-alpha
· $0.0000/Mtok out
openrouter/z-ai/glm-5.2:free
· $0.0000/Mtok out
openrouter/openrouter/auto
· $0.0000/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.