Alibaba Qwenopen weightsQwen3 Coder 30B A3B Instruct pricing
$0.07 per 1M input tokens and $0.28 per 1M output tokens. In real work that is 0.05¢ per chat answer and 0.17¢ to summarize a 20-page PDF.
What Qwen3 Coder 30B 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 | 0.05¢$0.45 / 1,000 | 88 in · 689 out · 909 reasoning | 51 of 336 | estimated |
| Reply to a customer email | 0.02¢$0.21 / 1,000 | 326 in · 98 out · 587 reasoning | 55 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.45¢$4.49 / 1,000 | 104 in · 0 out · 16,000 reasoning | 115 of 336 | estimated |
| Write 10 product descriptions | ≥0.45¢$4.50 / 1,000 | 345 in · 0 out · 16,000 reasoning | 140 of 336 | estimated |
| Translate 1,000 words | 0.05¢$0.46 / 1,000 | 1,386 in · 1,166 out · 136 reasoning | 30 of 336 | estimated |
| Proofread one page (500 words) | 0.06¢$0.57 / 1,000 | 777 in · 671 out · 1,159 reasoning | 63 of 336 | estimated |
| Summarize a 20-page PDF | 0.17¢$1.66 / 1,000 | 13,119 in · 501 out · 2,141 reasoning | 51 of 336 | estimated |
| Extract data from an invoice | 0.06¢$0.64 / 1,000 | 501 in · 561 out · 1,617 reasoning | 66 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.49¢$4.92 / 1,000 | 6,357 in · 0 out · 16,000 reasoning | 66 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.11¢$1.07 / 1,000 | 3,751 in · 974 out · 1,912 reasoning | 60 of 336 | estimated |
| Classify 100 support tickets | 0.25¢$2.46 / 1,000 | 1,463 in · 534 out · 7,879 reasoning | 89 of 336 | estimated |
| Review 500 lines of code | ≥0.48¢$4.82 / 1,000 | 4,874 in · 0 out · 16,000 reasoning | 83 of 336 | estimated |
| Write a SQL query | 0.07¢$0.75 / 1,000 | 177 in · 405 out · 2,225 reasoning | 74 of 336 | estimated |
| Run a 50-step coding agent | 19¢$185 / 1,000 | 2,259,875 in · 15,150 out · 80,850 reasoning | 91 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Qwen3 Coder 30B A3B Instruct through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 SiliconFlowfp8 | $0.07 / $0.28 | - | 262K | 100% |
 Amazon Bedrockunknown | $0.15 / $0.60 | - | 262K |
Price history
First seen in our price history on Sep 4, 2025 at $0.052 input / $0.21 output. Since then the output price moved from $0.21 to $0.28 per 1M tokens (5 changes).
FAQ
How much does Qwen3 Coder 30B A3B Instruct cost?
Qwen3 Coder 30B A3B Instruct costs $0.07 per 1 million input tokens and $0.28 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.05¢ and summarizing a 20-page PDF about 0.17¢.
Where is Qwen3 Coder 30B A3B Instruct cheapest?
Among 2 providers we track, the lowest list price today is at SiliconFlow: $0.07 input and $0.28 output per 1M tokens.
Is the Qwen3 Coder 30B A3B Instruct cost per task measured or estimated?
Estimated: Qwen3 Coder 30B 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.