Qwen3 32B
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.
- Organization
- Alibaba
- Family
- qwen
- Providers
- 13
- Context
- 131,072
- Output limit
- 16,384
- Knowledge
- 2025-04
- Release
- 2025-04
- Updated
- 2025-04
- Weights
- Open
- Input
- text
- Output
- text
- Capabilities
- Tools, Reasoning, Temperature
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Abacus | Qwen/Qwen3-32B | 131,072 | 8,192 | $0.09 / $0.29 | Yes | Yes | — | View |
| Amazon Bedrock | qwen.qwen3-32b-v1:0 | 32,768 | 16,384 | $0.15 / $0.60 | Yes | Yes | Yes | View |
| Chutes | Qwen/Qwen3-32B-TEE | 40,960 | 40,960 | $0.104 / $0.416 | Yes | Yes | Yes | View |
| Cortecs | qwen3-32b | 16,384 | 16,384 | $0.179 / $0.697 | Yes | Yes | Yes | View |
| Deep Infra | Qwen/Qwen3-32B | 40,960 | 16,384 | $0.08 / $0.28 | Yes | Yes | Yes | View |
| DevPass (LLM Gateway) | qwen3-32b | 40,960 | 16,384 | $0.36 / $0.87 | Yes | Yes | — | View |
| Hugging Face | Qwen/Qwen3-32B | 131,072 | 16,384 | $0.29 / $0.59 | Yes | Yes | Yes | View |
| Kilo Gateway | qwen/qwen3-32b | 40,960 | 16,384 | $0.08 / $0.28 | Yes | Yes | Yes | View |
| LLM Gateway | scx-ai/qwen3-32b | 32,768 | 8,192 | $0.36 / $0.87 | Yes | Yes | No | View |
| Merge Gateway | qwen/qwen3-32b | 131,072 | 32,768 | $0.15 / $0.60 | Yes | Yes | No | View |
| NanoGPT | qwen/qwen3-32b | 41,000 | 32,768 | $0.10 / $0.30 | No | Yes | No | View |
| DeepInfravia OpenRouter | qwen/qwen3-32b fp8 | 40,960 | 16,384 | $0.08 / $0.28 | Yes | Yes | Yes | View |
| SiliconFlowvia OpenRouter | qwen/qwen3-32b fp8 | 131,072 | 117,964 | $0.14 / $0.57 | Yes | Yes | Yes | View |
| Tenstorrentvia OpenRouter | qwen/qwen3-32b fp8 | 41,000 | 16,400 | $0.14 / $0.40 | Yes | No | No | View |
| Pioneer | Qwen/Qwen3-32B | 131,072 | 8,192 | $0.90 / $0.90 | Yes | Yes | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
qwen/qwen3-32bObserved - Input
- $0.08
- Output
- $0.28
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| DeepInfradeepinfra/fp8 | $0.08 | $0.28 | — | — |
| SiliconFlowsiliconflow/fp8 | $0.14 | $0.57 | — | — |
| Tenstorrenttenstorrent/fp8 | $0.14 | $0.40 | $0.09 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 3 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| DeepInfradeepinfra/fp8 | 350 ms | 483 ms | 920 ms | 2,185.09 ms |
| SiliconFlowsiliconflow/fp8 | 1,150 ms | 1,318.5 ms | 1,586.2 ms | 5,396.02 ms |
| Tenstorrenttenstorrent/fp8 | 467 ms | 514 ms | 765.4 ms | 2,022.24 ms |
Output throughput · tokens per second
All throughput percentiles 3 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| DeepInfradeepinfra/fp8 | 31 t/s | 33 t/s | 35 t/s | 38 t/s |
| SiliconFlowsiliconflow/fp8 | 44 t/s | 50.25 t/s | 57 t/s | 64 t/s |
| Tenstorrenttenstorrent/fp8 | 42 t/s | 45 t/s | 47 t/s | 48.69 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
qwen/qwen3-32bObserved Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| Composite indices | Qwen3 32B (Reasoning)qwen/qwen3-32b-04-28 | Artificial Analysis | Intelligence — · Coding 15.3 · Agentic 0.9 | Details |
| gpqa diamond | Qwen: Qwen3 32Bqwen/qwen3-32b-04-28 | OpenRouter | 60.906% | Details |
| tau bench verified airline | Qwen: Qwen3 32Bqwen/qwen3-32b-04-28 | OpenRouter | 47.833% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
qwen/qwen3-32bObserved - Context
- 131,072
- Maximum output
- 16,384
- Tokenizer
- Qwen3
- Input
- text
- Output
- text
- Moderation
- No
- Instruction format
- qwen3
- Knowledge cutoff
- 2025-03-31
- Added to OpenRouter
- 2025-04-28
https://openrouter.ai/api/v1qwen/qwen3-32bqwen/qwen3-32b-04-28Qwen/Qwen3-32BReasoning
- Required
- No
- Enabled by default
- Not reported
- Default effort
- —
- Supported efforts
- —
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Qwen3 32B cost?
Listed rates start at $0.08 per million input tokens and $0.28 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Qwen3 32B?
There are 15 cataloged offers across 13 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.
Resources
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
c50132c026a5 - ·
6c14eb087610