Qwen3.6 35B A3B pricing & benchmarks
Qwen3.6 35B A3B is available from Alibaba at $0.100 per million input tokens and $0.950 per million output tokens ($0.313 blended at 3:1). It accepts up to 262,144 tokens of context. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Pricing
Per million tokens · OpenRouter
Input$0.100
Output$0.950
Blended (3:1)$0.313
Specification
qwen/qwen3.6-35b-a3b
Context window262K
Max output236K
ReleasedApr 2026
LicenceOpen weights
Modalitiesin:text, in:image, in:video, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 84.8% ±2.6 | no thinking effort | 2026-08-07 | Independently run · Epoch AI |
| FrontierMath T1–3 | 20.4% ±2.4 | no thinking effort | 2026-08-30 | Independently run · Epoch AI |
| OTIS Mock AIME | 86.7% ±5.1 | thinking effort | 2026-08-07 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Where to run Qwen3.6 35B A3B
10 hosts · 3.0× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Darkbloom | $0.212 | $0.050 / $0.700 | 262K | fp4 | 100.0% |
| AkashML | $0.300 | $0.100 / $0.900 | 262K | fp8 | 100.0% |
| DeepInfra | $0.313 | $0.100 / $0.950 | 262K | fp8 | 97.9% |
| Parasail | $0.313 | $0.100 / $0.950 | 262K | fp8 | 100.0% |
| DekaLLM | $0.325 | $0.100 / $1.00 | 262K | — | 100.0% |
| Venice | $0.325 | $0.100 / $1.00 | 256K | fp8 | 99.9% |
| Phala | $0.468 | $0.200 / $1.27 | 262K | — | 95.1% |
| CoreWeave | $0.500 | $0.250 / $1.25 | 262K | fp8 | 99.9% |
| AtlasCloud | $0.500 | $0.250 / $1.25 | 262K | fp8 | 99.2% |
| SiliconFlow | $0.630 | $0.240 / $1.80 | 262K | fp8 | 96.6% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3.6 35B A3B
FAQ
How much does Qwen3.6 35B A3B cost?
Qwen3.6 35B A3B costs $0.100 per million input tokens and $0.950 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.313 per million tokens.
What is Qwen3.6 35B A3B's context window?
Qwen3.6 35B A3B accepts up to 262,144 tokens of context, and can generate up to 235,929 output tokens.
How good is Qwen3.6 35B A3B on benchmarks?
Qwen3.6 35B A3B scores 84.8% on GPQA Diamond, independently run and published by Epoch AI. 3 benchmark results are listed on this page, each with its run date and source.