As of August 25, 2026, Qwen3 235B A22B is 63% cheaper per million tokens than Qwen3 30B A3B. Qwen3 235B A22B is $0.10 / $0.10 per million input/output tokens versus Qwen3 30B A3B at $0.10 / $0.44. Source: https://bailian.console.aliyun.com/
Source: Qwen pricing (https://bailian.console.aliyun.com/)
Qwen3 235B A22B
Qwen
Input
$0.10
Output
$0.10
Qwen3 30B A3B
Qwen
Input
$0.10
Output
$0.44
Token pricing, specs, and benchmarks side by side
Each bar is share of the current leader on that eval. Click a row to open the board.
BFCL. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.
Qwen3 235B A22BQwen3 30B A3BVerdict
Qwen3 235B A22B offers both lower pricing and stronger benchmark performance across the board, making it the clear value leader in this comparison.
As of August 25, 2026, Qwen3 235B A22B is 63% cheaper on blended LLM API pricing. Qwen3 235B A22B costs $0.10 per million input tokens and $0.10 per million output tokens ($0.20 blended 1M-in + 1M-out). Qwen3 30B A3B costs $0.10 / $0.44 per million tokens ($0.54 blended). Sources: https://bailian.console.aliyun.com/ and https://bailian.console.aliyun.com/. The cheapest LLM for your app still depends on how many output tokens you generate.
Qwen3 235B A22B Qwen API pricing is $0.10 input and $0.10 output per million tokens via Qwen. Qwen3 30B A3B Qwen API pricing is $0.10 input and $0.44 output per million tokens via Qwen. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Qwen3 235B A22B leads on LiveCodeBench: Qwen3 235B A22B at 70.7% vs Qwen3 30B A3B at 62.6%. SWE-bench measures real GitHub fixes; LiveCodeBench measures contest programming.
Qwen3 235B A22B supports a 128K token context window, while Qwen3 30B A3B supports 128K tokens. Both models have the same context window size. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Qwen3 235B A22B leads on 7 of 8 shared benchmarks versus Qwen3 30B A3B's 1 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Qwen3 235B A22B and Qwen3 30B A3B are production API models. For cost-sensitive production traffic, Qwen3 235B A22B has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Qwen3 235B A22B through Qwen and Qwen3 30B A3B through Qwen with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Qwen API pricing and Qwen API pricing, quoted per million tokens. Official rate sheets: https://bailian.console.aliyun.com/ and https://bailian.console.aliyun.com/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Qwen3 235B A22B supports up to 128K output tokens per request, while Qwen3 30B A3B supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Qwen3 235B A22B runs at approximately 68.2 tokens/second while Qwen3 30B A3B runs at 88.8 tokens/second. Qwen3 30B A3B is faster in raw throughput. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Qwen3 235B A22B or Qwen3 30B A3B from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Qwen3 235B A22B costs $0.10/M input and $0.10/M output. Qwen3 30B A3B costs $0.10/M input and $0.44/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
