Alibaba Qwenopen weightsQwen3 VL 235B A22B Instruct pricing
$0.21 per 1M input tokens and $1.90 per 1M output tokens. In real work that is 0.31¢ per chat answer and 0.78¢ to summarize a 20-page PDF.
What Qwen3 VL 235B A22B 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 | 0.31¢$3.05 / 1,000 | 88 in · 689 out · 909 reasoning | 196 of 336 | estimated |
| Reply to a customer email | 0.14¢$1.37 / 1,000 | 326 in · 98 out · 587 reasoning | 194 of 336 | estimated |
| Write a 1,500-word blog post | ≥3.0¢$30.42 / 1,000 | 104 in · 0 out · 16,000 reasoning | 270 of 336 | estimated |
| Write 10 product descriptions | ≥3.0¢$30.47 / 1,000 | 345 in · 0 out · 16,000 reasoning | 284 of 336 | estimated |
| Translate 1,000 words | 0.28¢$2.76 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 119 of 336 | estimated |
| Proofread one page (500 words) | 0.36¢$3.64 / 1,000 | 777 in · 671 out · 1,159 reasoning | 195 of 336 | estimated |
| Summarize a 20-page PDF | 0.78¢$7.77 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 165 of 336 | estimated |
| Extract data from an invoice | 0.42¢$4.24 / 1,000 | 501 in · 561 out · 1,617 reasoning | 211 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥3.2¢$31.73 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 194 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.63¢$6.27 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 195 of 336 | estimated |
| Classify 100 support tickets | 1.6¢$16.29 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 239 of 336 | estimated |
| Review 500 lines of code | ≥3.1¢$31.42 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 225 of 336 | estimated |
| Write a SQL query | 0.50¢$5.03 / 1,000 | 177 in · 405 out · 2,225 reasoning | 228 of 336 | estimated |
| Run a 50-step coding agent | 42¢$417 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 152 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen3 VL 235B A22B Instruct through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.20 / $0.88 | $0.11 | 262K | 100% |
| V Venicefp8 | $0.21 / $1.90 | $0.10 | 128K | 93% |
 Parasailfp8 | $0.21 / $1.90 | $0.10 | 131K | 100% |
Price history
First seen in our price history on Oct 1, 2025 at $0.30 input / $1.50 output. Since then the output price moved from $1.50 to $1.90 per 1M tokens (10 changes).
FAQ
How much does Qwen3 VL 235B A22B Instruct cost?
Qwen3 VL 235B A22B Instruct costs $0.21 per 1 million input tokens and $1.90 per 1 million output tokens, with cached input at $0.10 (list price on Oct 18, 2026). In practice one chat answer costs about 0.31¢ and summarizing a 20-page PDF about 0.78¢.
Where is Qwen3 VL 235B A22B Instruct cheapest?
Among 3 providers we track, the lowest list price today is at DeepInfra: $0.20 input and $0.88 output per 1M tokens.
Is the Qwen3 VL 235B A22B Instruct cost per task measured or estimated?
Estimated: Qwen3 VL 235B A22B Instruct was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Alibaba Qwen. Real usage can differ.