Qwen3 32B
DeprecatedQwen3 32B is Alibaba's language model with a 131K context window and up to 41K output tokens, available from 10 providers, starting at $0.05 / 1M input and $0.1 / 1M output. A dense 32B-parameter LLM from the Qwen3 series with strong reasoning and tool-use capabilities, suitable for a wide range of language tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #364 |
| Coding Index | #169 |
| Math Index | #114 |
| MMLU-Pro | #132 |
| GPQA | #300 |
| HLE | #288 |
| LiveCodeBench | #153 |
| AIME | #25 |
| IFBench | #302 |
| Time to First Token | #469 |
| SciCode | #255 |
| MATH-500 | #41 |
| AIME 2025 | #114 |
| LCR | #440 |
| TerminalBench Hard | #309 |
| TAU2 | #259 |
| Output TPS | #240 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Fast | Batch | ||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.15 | $0.6 | $0.075 | $0.3 | $0.263 | $1.05 | $0.075 | $0.3 | |
| $0.4 | $0.8 | — | — | — | — | — | — | |
| $0.08 | $0.28 | — | — | — | — | — | — | |
| $0.9 | $0.9 | — | — | — | — | — | — | |
| $0.05 | $0.1 | — | — | — | — | — | — | |
| $0.1 | $0.45 | — | — | — | — | — | — | |
| $0.08 | $0.28 | — | — | — | — | — | — | |
| $0.08 | $0.23 | — | — | — | — | — | — | |
| $0.18 | $0.72 | — | — | — | — | $0.09 | $0.36 | |
| $0.15 | $0.6 | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen3 32B, ranked by cheapest on-demand price. The model needs about 77 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
| g7e.2xlarge |  AWS | RTX PRO Server 6000 | 96 GB | $3.36/hr | ||
| Standard_NC24ads_A100_v4 | Azure | NVIDIA A100 | 80 GB | $3.67/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Voyage 4 Nano | — | — | — | — | Available |
| Qwen3 Embedding 0.6B | 33K | $0.010 | — | Available | |
| Qwen3 Embedding 4B | 41K | $0.020 | — | Available | |
| Qwen3 Embedding 8B | 41K | $0.010 | — | Available | |
| Qwen3 32B | 131K | $0.050 | $0.100 | Current | |
| Qwen3 14B | 131K | $0.120 | $0.200 | Deprecated | |
| Qwen3 8B | 131K | $0.035 | $0.138 | Deprecated | |
| Qwen3 4B Instruct | — | 262K | $0.200 | $0.200 | Available |
| Qwen3 1.7B | — | 131K | $0.100 | $0.100 | Available |
| Qwen3 0.6B | — | 41K | $0.100 | $0.100 | Available |
| KwaiPilot KAT 32B Dev | — | 131K | $0.900 | $0.900 | Available |