Alibaba Qwenopen weightsQwen3.6 35B A3B pricing
$0.15 per 1M input tokens and $1.00 per 1M output tokens. In real work that is 0.16¢ per chat answer and 0.46¢ to summarize a 20-page PDF.
What Qwen3.6 35B A3B 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 | 0.16¢$1.61 / 1,000 | 88 in · 689 out · 909 reasoning | 140 of 336 | estimated |
| Reply to a customer email | 0.07¢$0.73 / 1,000 | 326 in · 98 out · 587 reasoning | 139 of 336 | estimated |
| Write a 1,500-word blog post | ≥1.6¢$16.02 / 1,000 | 104 in · 0 out · 16,000 reasoning | 220 of 336 | estimated |
| Write 10 product descriptions | ≥1.6¢$16.05 / 1,000 | 345 in · 0 out · 16,000 reasoning | 252 of 336 | estimated |
| Translate 1,000 words | 0.15¢$1.51 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 83 of 336 | estimated |
| Proofread one page (500 words) | 0.19¢$1.95 / 1,000 | 777 in · 671 out · 1,159 reasoning | 148 of 336 | estimated |
| Summarize a 20-page PDF | 0.46¢$4.61 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 119 of 336 | estimated |
| Extract data from an invoice | 0.23¢$2.25 / 1,000 | 501 in · 561 out · 1,617 reasoning | 159 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥1.7¢$16.95 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 148 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.34¢$3.45 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 138 of 336 | estimated |
| Classify 100 support tickets | 0.86¢$8.63 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 194 of 336 | estimated |
| Review 500 lines of code | ≥1.7¢$16.73 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 193 of 336 | estimated |
| Write a SQL query | 0.27¢$2.66 / 1,000 | 177 in · 405 out · 2,225 reasoning | 183 of 336 | estimated |
| Run a 50-step coding agent | 22¢$217 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 104 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen3.6 35B A3B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| D Darkbloomfp4 | $0.05 / $0.70 | $0.025 | 262K | 73% |
| A AkashMLfp8 | $0.10 / $0.90 | $0.05 | 262K | 100% |
 DeepInfrafp8 | $0.10 / $0.95 | $0.10 | 262K | 85% |
| D DekaLLMunknown | $0.10 / $1.00 | $0.05 | 262K | 100% |
| V Venicefp8 | $0.10 / $1.00 | - | 256K | 100% |
 Parasailfp8 | $0.15 / $1.00 | $0.05 | 262K | 100% |
| C CoreWeavefp8 | $0.25 / $1.25 | $0.25 | 262K | 100% |
| A AtlasCloudfp8 | $0.25 / $1.25 | $0.25 | 262K | 100% |
| P Phalaunknown | $0.20 / $1.27 | $0.056 | 262K | 100% |
 SiliconFlowfp8 | $0.24 / $1.80 | $0.15 | 262K | 100% |
Price history
First seen in our price history on Apr 27, 2026 at $0.16 input / $0.97 output. Since then the output price moved from $0.97 to $1.00 per 1M tokens (10 changes).
FAQ
How much does Qwen3.6 35B A3B cost?
Qwen3.6 35B A3B costs $0.15 per 1 million input tokens and $1.00 per 1 million output tokens, with cached input at $0.05 (list price on Oct 18, 2026). In practice one chat answer costs about 0.16¢ and summarizing a 20-page PDF about 0.46¢.
Where is Qwen3.6 35B A3B cheapest?
Among 10 providers we track, the lowest list price today is at Darkbloom: $0.05 input and $0.70 output per 1M tokens.
Is the Qwen3.6 35B A3B cost per task measured or estimated?
Estimated: Qwen3.6 35B A3B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Alibaba Qwen. Real usage can differ.