Qwen3 32B vs Qwen3 30B A3B API pricing
Updated
Qwen3 32B: USD 0.08 input, USD 0.28 output per 1M tokens (DeepInfra). Qwen3 30B A3B: USD 0.051 input, USD 0.335 output per 1M tokens (Cloudflare Workers AI). At 3 input tokens per output token, Qwen3 32B costs 6.6% more than Qwen3 30B A3B (USD 0.13 vs USD 0.122 per 1M).
How do Qwen3 32B and Qwen3 30B A3B differ on price?
- Cheapest input price: Qwen3 30B A3B USD 0.051 against USD 0.08 per 1M tokens, so Qwen3 32B costs 1.57× as much (57% more).
- Cheapest output price: Qwen3 30B A3B USD 0.25 against USD 0.28 per 1M tokens, so Qwen3 32B costs 1.12× as much (12% more).
- Among the 201 indexed models, Qwen3 32B ranks 32nd cheapest and Qwen3 30B A3B 28th on the 3:1 blend.
- No input:output mix changes the answer: Qwen3 30B A3B is cheaper at every mix before cache discounts.
- Only Qwen3 32B lists a cached-input discount: Qwen3 32B at 1 standard price of 5, from USD 0.0816 (Featherless, 20% below that provider's input price). Qwen3 30B A3B's cached tokens bill at the input price.
- Qwen3 32B states up to 131,072 tokens of context, 3.2× the 40,960 of Qwen3 30B A3B.
- Qwen3 32B has 5 providers with a standard price, 2 more than Qwen3 30B A3B; 2 providers sell both (DeepInfra and GMI Cloud).
- On one account, DeepInfra charges USD 0.13 for Qwen3 32B (its cheapest price) and USD 0.215 for Qwen3 30B A3B (1.76× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Qwen3 32B: its dearest standard price is 2× its cheapest, against 1.76× for Qwen3 30B A3B.
- Qwen3 32B has a batch price at 1 provider, from USD 0.1312 at 3:1 (Amazon Bedrock); Qwen3 30B A3B has no batch price on file.
- For the one-developer coding agent preset, the gap is USD 2,176 a year in Qwen3 30B A3B's favour (Qwen3 32B USD 303.30 a month, Qwen3 30B A3B USD 121.95).
- Per character of input, Qwen3 32B costs 1.57× as much as Qwen3 30B A3B in every measured language, because both use the Qwen3 32B tokenizer.
Qwen3 32B and Qwen3 30B A3B prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | Qwen3 32B | Qwen3 30B A3B |
|---|---|---|
| Model page | Qwen3 32B FP8 Qwen · 5 providers | Qwen3 30B A3B (fp8) Qwen · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.13 USD 0.08 in / USD 0.28 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.122 lower USD 0.051 in / USD 0.335 out at Cloudflare Workers AI Cloudflare Workers AI page checked 2026-11-14 |
| Cheapest input | USD 0.08 DeepInfra source | USD 0.051 lower Cloudflare Workers AI source |
| Cheapest cached input | USD 0.0816 Featherless source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.28 DeepInfra source | USD 0.25 lower GMI Cloud source |
| Maker's own API | Qwen publishes no paid standard price on its own API that we found. | Qwen publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.102 / USD 0.57 input / output, 5 prices | USD 0.08 / USD 0.335 input / output, 3 prices |
| Context window | 131,072 tokens, largest stated; from 32,768 at some providers | 40,960 tokens, largest stated; from 40,946 at some providers |
| Providers with a standard price | 5 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Qwen3 32B and Qwen3 30B A3B cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | Qwen3 32B | Qwen3 30B A3B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 12.24 DeepInfra | USD 10.62 Cloudflare Workers AI | USD 1.62 Qwen3 30B A3B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 23.40 DeepInfra | USD 17.26 Cloudflare Workers AI | USD 6.14 Qwen3 30B A3B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 303.30 SiliconFlow | USD 121.95 Cloudflare Workers AI | USD 181.35 Qwen3 30B A3B lower |
Qwen3 30B A3B is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.49× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
Qwen3 30B A3B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3 32B's, so the input:output ratio never changes the answer.
| Input : output tokens | Qwen3 32B | Qwen3 30B A3B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.23 DeepInfra | USD 0.2075 lower GMI Cloud |
| 1 : 1 | USD 0.18 DeepInfra | USD 0.165 lower GMI Cloud |
| 3 : 1 (the site’s blend) | USD 0.13 DeepInfra | USD 0.122 lower Cloudflare Workers AI |
| 10 : 1 (retrieval, long prompts) | USD 0.09818 DeepInfra | USD 0.07682 lower Cloudflare Workers AI |
| 30 : 1 (agents, big contexts) | USD 0.08645 DeepInfra | USD 0.06016 lower Cloudflare Workers AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Qwen3 32B and Qwen3 30B A3B cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Qwen3 32B tokenizer for Qwen3 32B (the same one for both, so the gap equals the price gap):
| Content | Qwen3 32B | Qwen3 30B A3B |
|---|---|---|
| English | USD 0.018 DeepInfra | USD 0.011 lower Cloudflare Workers AI |
| Arabic MSA | USD 0.031 DeepInfra | USD 0.020 lower Cloudflare Workers AI |
| Egyptian Arabic | USD 0.032 DeepInfra | USD 0.020 lower Cloudflare Workers AI |
| Hindi | USD 0.074 DeepInfra | USD 0.047 lower Cloudflare Workers AI |
| Chinese | USD 0.051 DeepInfra | USD 0.033 lower Cloudflare Workers AI |
| Spanish | USD 0.021 DeepInfra | USD 0.014 lower Cloudflare Workers AI |
| Code | USD 0.021 DeepInfra | USD 0.013 lower Cloudflare Workers AI |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- Qwen3 32B FP8 API pricing: all 5 providers and other tiers.
- Qwen3 30B A3B (fp8) API pricing: all 3 providers and other tiers.
- Cost calculator with Qwen3 32B and Qwen3 30B A3B preloaded
- Qwen3 token counter
- Prompt caching calculator
More comparisons: Gemma 4 26B A4B vs Qwen3 32B · Qwen3.5 27B vs Qwen3 32B · Qwen3 235B A22B vs Qwen3 32B · Gemma 4 26B A4B vs Qwen3 30B A3B · Qwen3.5 35B A3B vs Qwen3 30B A3B · Qwen3-30B-A3B-2507 vs Qwen3 30B A3B · Qwen3 30B A3B vs Qwen3-14B · every Qwen3 32B comparison · every Qwen3 30B A3B comparison · all 662 price comparisons
Questions
Is Qwen3 32B cheaper than Qwen3 30B A3B?
No. On a blend of 3 input tokens to 1 output token, Qwen3 30B A3B costs USD 0.122 per 1M tokens and Qwen3 32B USD 0.13, at each model's cheapest standard price. For input alone, Qwen3 30B A3B is cheaper (USD 0.051 against USD 0.08 per 1M); for output alone, Qwen3 30B A3B is (USD 0.25 against USD 0.28). This compares price only, not quality.
What do Qwen3 32B and Qwen3 30B A3B cost per 1M tokens?
Qwen3 32B: from USD 0.08 input and USD 0.28 output at DeepInfra; median of 5 standard prices USD 0.102 / USD 0.57. Qwen3 30B A3B: from USD 0.051 input and USD 0.335 output at Cloudflare Workers AI; median of 3 standard prices USD 0.08 / USD 0.335. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Qwen3 32B and Qwen3 30B A3B?
2 providers have a standard price for both: DeepInfra (USD 0.13 and USD 0.215 at 3:1), GMI Cloud (USD 0.225 and USD 0.1225 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.13 and USD 0.122.
Which is cheaper for a coding agent or a chatbot, Qwen3 32B or Qwen3 30B A3B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 303.30 a month on Qwen3 32B (SiliconFlow) against USD 121.95 on Qwen3 30B A3B (Cloudflare Workers AI), a difference of USD 181.35. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 12.24 a month on Qwen3 32B (DeepInfra) against USD 10.62 on Qwen3 30B A3B (Cloudflare Workers AI), a difference of USD 1.62. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of Qwen3 32B and Qwen3 30B A3B change?
Qwen3 30B A3B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3 32B's, so the input:output ratio never changes the answer.
Do Qwen3 32B and Qwen3 30B A3B have cached input pricing?
Qwen3 32B from USD 0.0816 per 1M cached input tokens (Featherless; 1 of 5 standard prices list a discount). Qwen3 30B A3B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, Qwen3 32B or Qwen3 30B A3B?
Qwen3 32B: up to 131,072 tokens, against 40,960 for Qwen3 30B A3B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- DeepInfra: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- SiliconFlow: pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- Amazon Bedrock: pricing (checked 2026-11-14)