Back to models
retired

Qwen: Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct

Prices

Input

$0.15 per 1M tokens

low
Output

$1.20 per 1M tokens

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

31 sales channels for this model.
ChannelWhatPrice
DatabricksInput$0.15 per 1M tokens
Input (cache write)$0.15 per 1M tokens
Input (cache write) (region: eu)$0.15 per 1M tokens
Input (cached read)$0.015 per 1M tokens
Input (cached read) (region: eu)$0.015 per 1M tokens
Input (region: eu)$0.15 per 1M tokens
Output$1.20 per 1M tokens
Output (region: eu)$1.20 per 1M tokens
Fireworks AI · fireworks-aiInput$0.90 per 1M tokens
Output$0.90 per 1M tokens
Alibaba Model Studio · aimlapiInput$0.1587 per 1M tokens
Output$1.27 per 1M tokens
Alibaba Model StudioInput$0.50 per 1M tokens
Output$2.00 per 1M tokens
Alibaba Model Studio · alibaba-cnInput$0.144 per 1M tokens
Output$0.574 per 1M tokens
Alibaba Model Studio · vercelInput$0.15 per 1M tokens
Output$1.20 per 1M tokens
OpenRouterInput$0.09 per 1M tokens
Input (cached read)$0.07 per 1M tokens
Output$1.10 per 1M tokens
OpenRouter · qwenInput$0.09 per 1M tokens
Input (cached read)$0.07 per 1M tokens
Output$1.10 per 1M tokens
Other · deepinfraInput$0.09 per 1M tokens
Output$1.10 per 1M tokens
Other · edenaiInput$0.15 per 1M tokens
Input (host: deepinfra)$0.09 per 1M tokens
Output$1.20 per 1M tokens
Output (host: deepinfra)$1.10 per 1M tokens
Other · gmiInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · heliconeInput$0.14 per 1M tokens
Output$1.40 per 1M tokens
Other · huggingfaceInput$0.25 per 1M tokens
Output$1.00 per 1M tokens
Other · huggingface-hyperbolicInput$0.30 per 1M tokens
Output$0.30 per 1M tokens
Other · huggingface-novitaInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · huggingface-togetherInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · io-netInput$0.1188 per 1M tokens
Input (cache write)$0.20 per 1M tokens
Input (cached read)$0.0594 per 1M tokens
Output$1.26 per 1M tokens
Other · jalapenoInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · jiekouInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · kiloInput$0.09 per 1M tokens
Input (cached read)$0.07 per 1M tokens
Output$1.10 per 1M tokens
Other · llmgatewayInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · llmgateway-providersInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · merge-gatewayInput$0.10 per 1M tokens
Input (cached read)$0.05 per 1M tokens
Output$1.10 per 1M tokens
Other · nano-gptInput$0.09 per 1M tokens
Input (cached read)$0.045 per 1M tokens
Output$1.10 per 1M tokens
Other · neonInput$0.15 per 1M tokens
Output$1.20 per 1M tokens
Other · novitaInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · novita-aiInput$0.15 per 1M tokens
Output$1.50 per 1M tokens
Other · nvidiaInput$0.00 per 1M tokens
Output$0.00 per 1M tokens
Other · openrouterInput$0.09 per 1M tokens
Output$1.10 per 1M tokens
Other · qiniu-aiInput$0.1449 per 1M tokens
Input (cached read)$0.0588 per 1M tokens
Output$0.5797 per 1M tokens
Other · together-aiInput$0.15 per 1M tokens
Output$1.50 per 1M tokens

Specifications

Provider
qwen
Context window
262,144
Max output tokens
262,144
Open weights
yes
Released
09/01/2025
Retires
04/02/2026
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
0.15 per 1M tokens, unchanged since 09/14/2026
Output
1.2 per 1M tokens, unchanged since 09/14/2026

Last updated 11/16/2026, 01:12