Alibaba Qwenopen weightsQwen3.5-122B-A10B pricing
$0.26 per 1M input tokens and $2.08 per 1M output tokens. In real work that is 0.33¢ per chat answer and 0.89¢ to summarize a 20-page PDF.
What Qwen3.5-122B-A10B 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 | 0.33¢$3.35 / 1,000 | 88 in · 689 out · 909 reasoning | 204 of 336 | estimated |
| Reply to a customer email | 0.15¢$1.51 / 1,000 | 326 in · 98 out · 587 reasoning | 202 of 336 | estimated |
| Write a 1,500-word blog post | ≥3.3¢$33.31 / 1,000 | 104 in · 0 out · 16,000 reasoning | 280 of 336 | estimated |
| Write 10 product descriptions | ≥3.3¢$33.37 / 1,000 | 345 in · 0 out · 16,000 reasoning | 291 of 336 | estimated |
| Translate 1,000 words | 0.31¢$3.07 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 126 of 336 | estimated |
| Proofread one page (500 words) | 0.40¢$4.01 / 1,000 | 777 in · 671 out · 1,159 reasoning | 209 of 336 | estimated |
| Summarize a 20-page PDF | 0.89¢$8.91 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 173 of 336 | estimated |
| Extract data from an invoice | 0.47¢$4.66 / 1,000 | 501 in · 561 out · 1,617 reasoning | 220 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥3.5¢$34.93 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 205 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.70¢$6.98 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 205 of 336 | estimated |
| Classify 100 support tickets | 1.8¢$17.88 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 250 of 336 | estimated |
| Review 500 lines of code | ≥3.5¢$34.55 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 232 of 336 | estimated |
| Write a SQL query | 0.55¢$5.52 / 1,000 | 177 in · 405 out · 2,225 reasoning | 235 of 336 | estimated |
| Run a 50-step coding agent | 79¢$787 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 213 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen3.5-122B-A10B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 SiliconFlowfp8 | $0.26 / $2.08 | - | 262K | 100% |
 Alibabaunknown | $0.26 / $2.08 | - | 262K | 100% |
| A AtlasCloudfp8 | $0.30 / $2.40 | $0.30 | 262K | 100% |
 Novitabf16 | $0.40 / $3.20 | - | 262K | 100% |
Price history
First seen in our price history on Mar 3, 2026 at $0.40 input / $3.20 output. Since then the output price moved from $3.20 to $2.08 per 1M tokens (6 changes).
FAQ
How much does Qwen3.5-122B-A10B cost?
Qwen3.5-122B-A10B costs $0.26 per 1 million input tokens and $2.08 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.33¢ and summarizing a 20-page PDF about 0.89¢.
Where is Qwen3.5-122B-A10B cheapest?
Among 4 providers we track, the lowest list price today is at SiliconFlow: $0.26 input and $2.08 output per 1M tokens.
Is the Qwen3.5-122B-A10B cost per task measured or estimated?
Estimated: Qwen3.5-122B-A10B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Alibaba Qwen. Real usage can differ.