Alibaba Qwenopen weightsQwen3 Next 80B A3B Instruct pricing
$0.09 per 1M input tokens and $1.10 per 1M output tokens. In real work that is 0.18¢ per chat answer and 0.41¢ to summarize a 20-page PDF.
What Qwen3 Next 80B A3B Instruct costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.18¢$1.77 / 1,000 | 88 in · 689 out · 909 reasoning | 149 of 336 | estimated |
| Reply to a customer email | 0.08¢$0.78 / 1,000 | 326 in · 98 out · 587 reasoning | 146 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.8¢$17.61 / 1,000 | 104 in · 0 out · 16,000 reasoning | 229 of 336 | estimated |
| Write 10 product descriptions | ≥1.8¢$17.63 / 1,000 | 345 in · 0 out · 16,000 reasoning | 263 of 336 | estimated |
| Translate 1,000 words | 0.16¢$1.56 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 87 of 336 | estimated |
| Proofread one page (500 words) | 0.21¢$2.08 / 1,000 | 777 in · 671 out · 1,159 reasoning | 159 of 336 | estimated |
| Summarize a 20-page PDF | 0.41¢$4.09 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 111 of 336 | estimated |
| Extract data from an invoice | 0.24¢$2.44 / 1,000 | 501 in · 561 out · 1,617 reasoning | 178 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.8¢$18.17 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 156 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.35¢$3.51 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 141 of 336 | estimated |
| Classify 100 support tickets | 0.94¢$9.39 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 200 of 336 | estimated |
| Review 500 lines of code | ≥1.8¢$18.04 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 199 of 336 | estimated |
| Write a SQL query | 0.29¢$2.91 / 1,000 | 177 in · 405 out · 2,225 reasoning | 191 of 336 | estimated |
| Run a 50-step coding agent | 31¢$309 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 131 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen3 Next 80B A3B Instruct through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.072 / $0.88 | - | 262K | |
DeepInfrafp8 | $0.09 / $1.10 | - | 262K | 100% |
 Parasailfp8 | $0.10 / $1.10 | $0.07 | 262K | 100% |
 Googleunknown | $0.15 / $1.20 | - | 262K | 100% |
DeepInfrafp8 | $0.14 / $1.65 | - | 262K | 100% |
Price history
First seen in our price history on Sep 16, 2025 at $0.098 input / $0.39 output. Since then the output price moved from $0.39 to $1.10 per 1M tokens (10 changes).
FAQ
How much does Qwen3 Next 80B A3B Instruct cost?
Qwen3 Next 80B A3B Instruct costs $0.09 per 1 million input tokens and $1.10 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.18¢ and summarizing a 20-page PDF about 0.41¢.
Where is Qwen3 Next 80B A3B Instruct cheapest?
Among 5 providers we track, the lowest list price today is at DeepInfra: $0.072 input and $0.88 output per 1M tokens.
Is the Qwen3 Next 80B A3B Instruct cost per task measured or estimated?
Estimated: Qwen3 Next 80B A3B Instruct was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Alibaba Qwen. Real usage can differ.