# Qwen: Qwen3.6 35B A3B

- Model id: `qwen/qwen3.6-35b-a3b`
- Served by: -
- List price per 1M tokens, input / output, from: -, with 0% platform fee. A request is billed at the list price of the host that served it.
- Context: 262K, max output 236K
- Prices read 2026-11-15 09:33 UTC
- Page: https://plaingateway.com/models/qwen/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. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

## Hosts

| Host | Endpoint | In / out /M | Cache read /M | Context | Served |
|---|---|---|---|---|---|
| Primeintellect | `primeintellect/fp8` | $0.013 / $0.12 | $0.012 | 262K | no |
| Darkbloom | `darkbloom/fp4` | $0.05 / $0.70 | $0.025 | 262K | no |
| DeepInfra | `deepinfra/fp8/flex` | $0.08 / $0.76 | $0.08 | 262K | no |
| Coreweave | `coreweave/fp8` | $0.10 / $0.89 | $0.035 | 262K | no |
| Akashml | `akashml/fp8` | $0.10 / $0.90 | $0.05 | 262K | no |
| Parasail | `parasail/fp8` | $0.10 / $0.90 | $0.025 | 262K | no |
| DeepInfra | `deepinfra/fp8` | $0.10 / $0.95 | $0.10 | 262K | no |
| Dekallm | `dekallm` | $0.10 / $1.00 | $0.05 | 262K | no |
| Venice | `venice/fp8` | $0.10 / $1.00 | - | 256K | no |
| DeepInfra | `deepinfra/fp8/priority` | $0.15 / $1.43 | $0.15 | 262K | no |
| Atlas Cloud | `atlas-cloud/fp8` | $0.25 / $1.25 | $0.25 | 262K | no |
| Siliconflow | `siliconflow/fp8` | $0.24 / $1.80 | $0.15 | 262K | no |

## First request

```sh
curl https://api.plaingateway.com/api/v1/chat/completions \
  -H "Authorization: Bearer $PLAINGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen/qwen3.6-35b-a3b", "messages": [{"role": "user", "content": "Say hello in five words."}]}'
```

Sign up at https://plaingateway.com/signup (no card), create a key, send a test call, and add credits when you want more. New accounts may get a small starting credit. The whole bootstrap for agents: https://plaingateway.com/llms.txt