Today's price · per 1M tokens
Input
$0.160
per 1M tokens
Output
$0.640
per 1M tokens
Blended
$0.280
blended $/1M — 3:1 weighted input:output
How this price is scoped: Alibaba Model Studio International list price, one flat rate covering both Non-Thinking and Thinking modes, from the vendor's open-source Qwen table. No context-cache or batch rate is printed for this SKU, so cached input is left unset rather than assumed. The pricing page prints no context tier for this SKU; the 128K context is what Alibaba's own served endpoint reports. Alibaba's own gateway endpoint quotes a lower routed rate of $0.104/$0.416. Alibaba's pricing page states that it lists standard prices only and directs buyers to the Model Studio console for current offers, and this SKU's row carries no discount label, so the standard list rate is the one tracked here — the same basis as every other Alibaba row on this site.
Price receipt
We read Alibaba's own pricing page on and found qwen3-32b listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 4603ffb7a8.
Available on 3 hosts
cheapest blended first · $ per 1M tokensQwen3-32B is sold by 3 providers. Prices are per 1M tokens (blended = (3×input + 1×output) ÷ 4). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.
| Host | Input | Output | Blended | vs first-party |
|---|---|---|---|---|
| DeepInfra details → | $0.080 | $0.280 | $0.130 | -54% |
| Alibaba first-party | $0.160 | $0.640 | $0.280 | — |
| Groq details → | $0.290 | $0.590 | $0.365 | +30% |
Overview
Qwen3-32B served by Alibaba, the model's maker, on Model Studio. $0.16/$0.64 per 1M tokens, one flat rate covering both thinking and non-thinking modes. Open weights, 128K-token context, text-only.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is betterWe hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.
- AA-Omniscience Index: -50.4 (−100–100)
- LMSYS Chatbot Arena: 1347.1 ELO (Human preference)
- Ranks #170 of 194 comparably-measured models by percentile score, across 2 independent measurements
- Ranks #80 of 194 comparably-tested models by normalized performance per dollar
Source: Artificial Analysis, LMSYS Chatbot Arena (UC Berkeley) · updated · See full rankings →
Specifications
- Provider
- Alibaba
- Context window
- 131K tokens
- Modality
- text
- Parameters
- 32B
- Open source
- Yes — open weights available
- Released
- Status
- Current
- Last updated
- Tags
Availability verified: — listed on Alibaba's own page