Qwen3.6 35B A3B
Qwen (Alibaba) · Open weights · 262K context · released Apr 27, 2026 · checked 8h ago
Ways to buy 9
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
| Darkbloom fp4 | $0.05 | $0.7 | $0.05 / $0.7Cheapest | n/a | Cheapest |
| AkashML fp8 · cached $0.05 | $0.1 | $0.9 | $0.1 / $0.9+41% vs cheapest | $0.05 | +41% vs cheapest |
 DeepInfrafp8 | $0.1 | $0.95 | $0.1 / $0.95+47% vs cheapest | n/a | +47% vs cheapest |
 Venicefp8 | $0.1 | $1 | $0.1 / $1+53% vs cheapest | n/a | +53% vs cheapest |
 Parasailfp8 · cached $0.05 | $0.15 | $1 | $0.15 / $1+71% vs cheapest | $0.05 | +71% vs cheapest |
| AtlasCloud fp8 · cached $0.186 | $0.186 | $1.11 | $0.186 / $1.11+97% vs cheapest | $0.186 | +97% vs cheapest |
| Phala Default region | $0.2 | $1.27 | $0.2 / $1.27+120% vs cheapest | n/a | +120% vs cheapest |
 CoreWeavefp8 · cached $0.25 | $0.25 | $1.25 | $0.25 / $1.25+135% vs cheapest | $0.25 | +135% vs cheapest |
 SiliconFlowfp8 · cached $0.15 | $0.24 | $1.8 | $0.24 / $1.8+196% vs cheapest | $0.15 | +196% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $19.00 direct.
Helicone$19.00+0%
Kong AI Gateway$19.00+0%
LiteLLM$19.00+0%
Vercel AI Gateway$19.00+0%
Cloudflare AI Gateway$19.95+5%
Requesty$19.95+5%
Eden AI$20.05+5.5%
OpenRouter$20.05+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Qwen3.8 Max Prime Qwen (Alibaba) · 1M | $4 | $12 | $4 / $12 | $6 | 1M | Lab list price | · |
| Qwen3.8 Omni Flash Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
| Qwen3.8 Max (0902) Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · |
| Qwen3.8 Flash Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · |
 DeepSeek V4.1 FlashDeepSeek · 1MCheapest: $0.131 on Morph | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.131 on Morph | · |
 GPT-6 LunaOpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Luna Pro OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
 Muse Spark 1.3 ContributorMeta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
About Qwen3.6 35B A3B
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.
Takes text, image, video in and returns text. First listed Sep 23, 2026. Up to 236K output tokens. Blended price $0.213 per 1M tokens at 3 input to 1 output. Model id qwen3-6-35b-a3b.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across fru.devCompany profile
Questions
How much does Qwen3.6 35B A3B cost?
$0.05 per million input tokens and $0.7 per million output tokens.
What is the context window of Qwen3.6 35B A3B?
262K tokens, with up to 236K tokens of output.
Where is Qwen3.6 35B A3B cheapest?
Of 9 routes tracked, Darkbloom is cheapest at $0.05 input and $0.7 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.