Qwen · live price
Qwen3.5-35B-A3B API pricing
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Small and cheap (under $1 per 1M)Tool callingReasoningimage inputvideo input
- Input
- $0.14
- per 1M tokens
- Output
- $1
- per 1M tokens
- Cached input
- $0.05
- per 1M tokens
- Context
- 262K
- 82K max output
List price from OpenRouter, which passes Qwen's price through without markup. Refreshed hourly. Released February 25, 2026. Model id qwen/qwen3.5-35b-a3b.
What Qwen3.5-35B-A3B costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$0.64
1,000 input + 500 output tokens each
1,000 RAG questions
$1.62
8,000 input + 500 output tokens each
100 coding-agent steps
$0.62
30,000 input + 2,000 output tokens each, no caching
Qwen3.5-35B-A3B price history
Price last changed on 2026-10-21. We record prices daily since 2026-10-01.
Qwen3.5-35B-A3B price by host
Darkbloom serves it below list price right now. Route to it to pay less on every token.
- Darkbloom$0.065 in · $0.75 out · 262K ctx · 100.0% uptime 24h
- DeepInfra$0.112 in · $0.8 out · 262K ctx · 100.0% uptime 24h
- Parasail$0.15 in · $1 out · 262K ctx · 99.3% uptime 24h
- Venice$0.15 in · $1 out · 256K ctx · 99.8% uptime 24h
- Alibaba$0.163 in · $1.30 out · 262K ctx · 100.0% uptime 24h
- SiliconFlow$0.24 in · $1.80 out · 262K ctx · 98.6% uptime 24h
Where to buy Qwen credits for less
Qwen3.5-35B-A3B costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Qwen3.5-35B-A3B cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$17.00/ month
Cheaper alternatives to Qwen3.5-35B-A3B
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax: MiniMax M3.1 Flash | $0.075 | $0.3 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| DeepSeek: DeepSeek V4.1 Flash | $0.05 | $0.199 |
Other Qwen models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Qwen3.5-27B | $0.26 | $2.60 |
| Qwen3.5-122B-A10B | $0.26 | $2.08 |
| Qwen3.5-Flash | $0.065 | $0.26 |
| Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 |
| Qwen3.5 397B A17B | $0.45 | $3 |
| Qwen3.5-9B | $0.17 | $0.25 |