Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Qwen3.5 35B A3B dottxt API

Open in consoleI need inference
  • 262KContext
  • –Max output
  • $0.35/ $1.20From, per 1M in / out
  • 1Provider
Providers
  • Doubleword

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
Doubleword$0.35$0.20$1.20

USD, as of October 28, 2026. Live prices

Cost

WorkloadDoubleword
1,000 chat replies2K in, 500 out each$1.30
1,000 agent tasks50K in, 5K out each$23.50
Monthly batch job500M in, 50M out$235.00

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.5-35b-a3b-dottxt",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the Qwen3.5 35B A3B dottxt API cost?

On RouterPlus, Qwen3.5 35B A3B dottxt costs $0.35 per million input tokens and $1.20 per million output tokens at Doubleword, the lowest listed prices and the provider where routing starts. Prices as of October 28, 2026.

Which providers serve Qwen3.5 35B A3B dottxt?

Doubleword serves Qwen3.5 35B A3B dottxt on RouterPlus today.

What is the Qwen3.5 35B A3B dottxt model ID?

Use "qwen/qwen3.5-35b-a3b-dottxt" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.

What is the Qwen3.5 35B A3B dottxt context window?

262K tokens of context and up to – output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is Qwen3.5 35B A3B dottxt open weights?

Yes. Qwen publishes Qwen3.5 35B A3B dottxt as an open-weight model, which is why several independent providers can host it.

Do any Qwen3.5 35B A3B dottxt providers retain prompts?

0 of 1 providers list no prompt retention. Doubleword may retain prompts. Pin the providers you accept with a routing policy.

Can I reserve capacity for Qwen3.5 35B A3B dottxt?

Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.

More Qwen

All Qwen modelsAll models

Need Qwen3.5 35B A3B dottxt at volume?

Open in consoleI need inference