Deprecated on Jul 17, 2026. 10 providers still list it at the prices below.
Context
131K
Max output
131K
Serving providers
10
Cheapest input
$0.08 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
74 t/s
tokens / second
Time to first token
1.32s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.0 | reasoning: true | — | |||||||||||||||||
| CritPt | 0% | reasoning: true | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 281.5 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 289.4 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 67% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 7% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 36% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 55% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 0% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 80% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -50.4 | reasoning: true | — | |||||||||||||||||
| Omniscience Accuracy | 0.2 | reasoning: true | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.2 | reasoning: true | — | |||||||||||||||||
| SciCode | 36% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Terminal Bench40 | 0 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 3% | reasoning: true | — | |||||||||||||||||
| TerminalBench v2.1 | 5% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 5% | reasoning: true | — | |||||||||||||||||
| τ²-bench | 30% | reasoning: true | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing detail
cost beyond the standard rate · source: models.devReasoning tokens
$8.40
per 1M · thinking output
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.08 to $0.90 per 1M tokens across 10 providers, so the dearest route costs 1025% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.08 | $0.28 | 1 | ||||||||||
Standarddeepinfra/Qwen/Qwen3-32B
| |||||||||||||
| OpenRouter | $0.08 | $0.28 | 1 | ||||||||||
Standardqwen/qwen3-32b
| |||||||||||||
| Ovhcloud | $0.08 | $0.23 | 1 | ||||||||||
Standardovhcloud/Qwen3-32B
| |||||||||||||
| Nebius | $0.10 | $0.30 | 1 | ||||||||||
Standardnebius/Qwen/Qwen3-32B
| |||||||||||||
| Amazon Bedrock | $0.15 | $0.60 | 1 | ||||||||||
Standardbedrock_mantle/qwen.qwen3-32b
| |||||||||||||
| VercelVercel reseller quote | $0.15 | $0.60 | 1 | ||||||||||
Standardalibaba/qwen-3-32b
| |||||||||||||
| Groq | $0.29 | $0.59 | 1 | ||||||||||
Standardgroq/qwen/qwen3-32b
| |||||||||||||
| Cerebras | $0.40 | $0.80 | 1 | ||||||||||
Standardcerebras/qwen-3-32b
| |||||||||||||
| Fireworks AI is dearest at $0.90 / $0.90 | |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 80% since first tracked
Cost calculator
estimate your monthly spend on this model$34
estimated / month
Model IDs
copy the exact identifier for your platformovhcloud/Qwen3-32Bqwen/qwen3-32bdeepinfra/Qwen/Qwen3-32Bnebius/Qwen/Qwen3-32Bbedrock_mantle/qwen.qwen3-32balibaba/qwen-3-32bgroq/qwen/qwen3-32bcerebras/qwen-3-32bsambanova/Qwen3-32Bfireworks_ai/accounts/fireworks/models/qwen3-32b
Frequently asked questions
Qwen3 32B pricing, context and availabilityIs Qwen3 32B still available?
Qwen3 32B was deprecated on 2026-07-17, but 10 serving providers still list it.
How much does Qwen3 32B cost?
Qwen3 32B costs $0.08 per 1M input tokens from DeepInfra, and $0.23 per 1M output tokens from Ovhcloud. Across 10 serving providers, input prices range from $0.08 to $0.90 per 1M tokens.
What is the context window of Qwen3 32B?
Qwen3 32B accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve Qwen3 32B?
Qwen3 32B is available from 10 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Qwen3 32B do?
Qwen3 32B supports tool use, reasoning and structured output.
Other Alibaba models
compare pricing across the Alibaba lineupQwen3 Next 80B A3B Instruct$0.09/1M · 11 providersQwen3 Next 80B A3B Thinking$0.14/1M · 10 providersQwen3.8 Max$1.65/1M · 10 providersQwen3.6 35B A3B$0.05/1M · 9 providersQwen3 VL 235B A22B Instruct$0.20/1M · 9 providersQwen2.5 Coder 32B Instruct$0.05/1M · 8 providersQwen3 235B A22b Instruct 2507$0.09/1M · 8 providersQwen3.6 27B$0.15/1M · 8 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI