Qwen3.6 35B A3B
Qwen3.6 35B A3B is Alibaba's language model with a 262K context window and up to 236K output tokens, available from 11 providers, starting at $0.05 / 1M input and $0.4 / 1M output. Alibaba's flagship Qwen3.6 MoE model with 35B total parameters and 3B activated per token, built with 256 experts and direct community feedback integration.
| Benchmarks | |
|---|---|
| Intelligence Index | #191 |
| Coding Index | #95 |
| GPQA | #116 |
| HLE | #133 |
| IFBench | #101 |
| Time to First Token | #490 |
| SciCode | #238 |
| LCR | #129 |
| TerminalBench Hard | #69 |
| TAU2 | #25 |
| Output TPS | #81 |
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video✓
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Batch | |||||
|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.254 | $1.52 | N/A | — | — | — | — | — | |
| $0.375 | $2.25 | N/A | — | — | — | $0.188 | $1.13 | |
| $0.1 | $0.95 | N/A | — | — | — | — | — | |
| $0.285 | $1.71 | N/A | — | — | — | — | — | |
| $0.15 | $0.5 | N/A | — | — | — | — | — | |
| $0.248 | $1.49 | N/A | — | — | — | — | — | |
| $0.1 | $0.95 | $0.1 | — | — | — | — | — | |
| $0.14 | $0.45 | N/A | — | — | — | — | — | |
| $0.05 | $0.4 | $0.02 | $0.05 | $0.4 | $0.02 | — | — | |
| $0.25 | $1.50 | N/A | — | — | — | — | — | |
| $0.25 | $1.25 | N/A | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen3.6 35B A3B, ranked by cheapest on-demand price. The model needs about 84 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 | ||
| g2-standard-48 |  GCP | 4× nvidia-l4 | 96 GB | $3.99/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 1.0M | $2.00 | $6.00 | Available | |
| Qwen Audio 3 Flash ASR | — | — | — | — | Available |
| Qwen Audio 3 Flash ASR Filetrans | — | — | — | — | Available |
| Qwen Audio 3 Flash ASR Streaming | — | — | — | — | Available |
| Qwen Audio 3 Flash Realtime | — | — | $0.230 | $0.930 | Available |
| Qwen Audio 3 Plus Realtime | — | — | $0.800 | $6.40 | Available |
| Qwen Audio 3 Plus TTS | — | — | — | — | Available |
| Qwen Audio 3.1 Plus Realtime | — | — | $0.800 | $6.40 | Available |
| Qwen Image 3 | — | — | — | — | Available |
| Qwen Image 3.0 Pro | — | — | — | — | Available |
| Qwen3.6 35B A3B | 262K | $0.050 | $0.400 | Current |