Loading…
Alibaba
qwen/qwen3.6-35b-a3b-20260415Hugging Face ↗
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...
OpenRouter share of tokens, by day.
Qwen: Qwen3.6 35B A3B holds 0.49% today, up from 0.21% at the start of the visible window.
Qwen: Qwen3.6 35B A3B's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-10-14, Qwen: Qwen3.6 35B A3B holds 0.5% of OpenRouter token share, up 0.17pp over 30 days. Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-14. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Qwen: Qwen3.6 35B A3B is served by 10 tracked endpoints on OpenRouter. The cheapest output price is $0.70 per million tokens from Darkbloom, and the most expensive is $1.80 from SiliconFlow. The largest context window offered is 262k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Darkbloom | $0.050 | $0.70 | 262k | 100.00% |
| AkashML | $0.100 | $0.90 | 262k | 100.00% |
| DeepInfra | $0.100 | $0.95 | 262k | 100.00% |
| DekaLLM | $0.100 | $1.00 | 262k | 100.00% |
| Venice | $0.100 | $1.00 | 256k | 100.00% |
| Parasail | $0.15 | $1.00 | 262k | 100.00% |
| CoreWeave | $0.25 | $1.25 | 262k | 100.00% |
| AtlasCloud | $0.25 | $1.25 | 262k | — |
| Phala | $0.20 | $1.27 | 262k | 100.00% |
| SiliconFlow | $0.24 | $1.80 | 262k | 100.00% |
Median dollars spent on one Qwen: Qwen3.6 35B A3B session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 2–9 turns | 10–49 turns |
|---|---|---|
| Hermes Agent | $0.0070 | $0.058 |
